© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 9553
    Prev
    Next
    INDEX
    Explanations

    text snippets from mathematical papers

    oai_token-act-pair · gemini-2.0-flash

    algebraic geometry

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    nourriture
    -0.61
     imprimée
    -0.59
    anskje
    -0.58
    nhi
    -0.56
    argout
    -0.54
    dafx
    -0.53
    MeasureSpec
    -0.52
     numberOfRows
    -0.51
    glTexCoord
    -0.51
    shafen
    -0.50
    POSITIVE LOGITS
     فريبيس
    0.77
    <bos>
    0.74
     للمعارف
    0.68
    ArrowToggle
    0.63
    يكب
    0.63
    NameInMap
    0.62
    Билгалдахарш
    0.57
    migrationBuilder
    0.56
    Jegyzetek
    0.56
    ThroughAttribute
    0.55
    Activations Density 3.429%

    No Known Activations