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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3600
    Prev
    Next
    INDEX
    Explanations

    words and phrases used to present an argument

    oai_token-act-pair · gemini-2.0-flash

    statements and arguments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    BeginContext
    -0.58
    AndEndTag
    -0.57
    олові
    -0.56
    oug
    -0.55
    ConstraintMaker
    -0.53
    CreateModel
    -0.50
    exitRule
    -0.49
     cung
    -0.48
    Razor
    -0.48
    rrggbb
    -0.48
    POSITIVE LOGITS
     beginnetje
    0.63
     HasFactory
    0.61
    parsedMessage
    0.54
     nahilalakip
    0.53
    SharedCtor
    0.52
    sizeCache
    0.50
     مشارکت‌کنندگان
    0.49
     dénon
    0.49
     незавершена
    0.49
    glDisable
    0.49
    Activations Density 22.452%

    No Known Activations