© 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-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3943
    Prev
    Next
    INDEX
    Explanations

    words or phrases enclosed in quotation marks and related to cultural traditions

    oai_token-act-pair · gemini-2.0-flash

    punctuation

    np_max-act-logits · gemini-2.0-flash

    opening punctuation

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Grecs
    -0.65
     enfans
    -0.63
     stället
    -0.61
     skolan
    -0.60
     morire
    -0.58
     dieux
    -0.57
    GDPR
    -0.57
     soldati
    -0.56
     fidèles
    -0.56
     Juifs
    -0.56
    POSITIVE LOGITS
    obut
    0.36
    OwnProperty
    0.34
     ID
    0.32
     CGPoint
    0.30
    TimerTask
    0.30
    ophenyl
    0.29
    obenzene
    0.29
     же
    0.29
    kyrie
    0.29
     AST
    0.28
    Activations Density 16.099%

    No Known Activations