© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 4046
    Prev
    Next
    INDEX
    Explanations

    statistics about an American football game

    oai_token-act-pair · gemini-2.0-flash

    sports scoring

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    PerformLayout
    -0.77
    migrationBuilder
    -0.66
     StatelessWidget
    -0.64
    tagHelperRunner
    -0.61
     виправивши
    -0.59
    ReusableCell
    -0.57
    PreferredItem
    -0.55
    BoxShadow
    -0.55
    Билгалдахарш
    -0.54
    StringCopy
    -0.54
    POSITIVE LOGITS
    dolu
    0.50
     punt
    0.49
    usercontent
    0.48
    듈
    0.48
    numerusform
    0.48
    reactivex
    0.48
     iyon
    0.48
     gezet
    0.47
    Staking
    0.46
     Plung
    0.46
    Activations Density 0.946%

    No Known Activations