© 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
    3. Gemma-3-4B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 2880
    Prev
    Next
    INDEX
    Explanations

    code comments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_5_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    etic
    0.65
    ethyl
    0.63
    ns
    0.62
    )}=
    0.58
    "}
    0.57
    ность
    0.57
    listBox
    0.56
    )}=\
    0.55
    scrollTo
    0.55
    "});
    0.54
    POSITIVE LOGITS
    ﺯ
    0.59
    ﺽ
    0.57
    ك
    0.55
    ν
    0.55
     radica
    0.54
    يں
    0.53
    ש
    0.53
    抜群
    0.53
     precedent
    0.53
    им
    0.53
    Activations Density 0.085%

    No Known Activations