© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 10420
    Prev
    Next
    INDEX
    Explanations

    trans prefix followed by specific suffixes

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron responds to any word containing the prefix “trans” (e.g. translate, transmit, transplant, transgender, transcribe, transatlantic, etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    words containing the “trans-” prefix or morpheme (e.g., forms indicating transfer, change, or across).

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    words with the prefix "trans" (transplant, transcribing, transatlantic, transgender, transposing, transmogrifier, transition, transferring, transmitted, translated).

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    unier
    0.70
    otard
    0.65
    obenz
    0.64
    אן
    0.59
    uin
    0.59
    িনি
    0.59
    ody
    0.57
    ogeny
    0.56
     scaff
    0.56
    ouin
    0.56
    POSITIVE LOGITS
     Trans
    1.66
    Trans
    1.55
     trans
    1.48
    trans
    1.38
     TRANS
    1.34
     ট্রান্স
    1.34
     ट्रांस
    1.24
     Тран
    1.21
    Transc
    1.20
     тран
    1.16
    Activations Density 0.128%

    No Known Activations