© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3781
    Prev
    Next
    INDEX
    Explanations

    periods followed by the digits 1, 2, 6, 7, 9, or 10

    oai_token-act-pair · gemini-2.0-flash

    Code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     Вікіпе
    -0.68
     intermédiaire
    -0.62
    ArgsConstructor
    -0.59
     vulgaires
    -0.59
    ViewImports
    -0.59
    rxjs
    -0.58
    jspx
    -0.57
    endpush
    -0.54
    áneo
    -0.54
    endmodule
    -0.53
    POSITIVE LOGITS
     betweenstory
    0.55
    ActionMode
    0.53
    tagHelperRunner
    0.52
    Carriera
    0.51
    res
    0.50
    etzt
    0.46
     exac
    0.46
     parch
    0.46
     impea
    0.45
    :][
    0.44
    Activations Density 0.073%

    No Known Activations