© 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. 4771
    Prev
    Next
    INDEX
    Explanations

    references to figures, tables, and genes in scientific papers

    oai_token-act-pair · gemini-2.0-flash

    Citations and code

    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
     թվական
    -0.55
    <bos>
    -0.55
    Hinweis
    -0.54
     <=",
    -0.52
    sejarah
    -0.52
    ^(@)
    -0.50
    ArrowToggle
    -0.48
    requent
    -0.48
    mäßige
    -0.48
     kaarangay
    -0.47
    POSITIVE LOGITS
     BorderRadius
    0.64
    Hentet
    0.57
    BuilderFactory
    0.53
    ArgsConstructor
    0.52
    endpush
    0.52
    parsedMessage
    0.52
    Aktualisiert
    0.52
    UserScript
    0.50
    TagMode
    0.50
    UnknownFields
    0.49
    Activations Density 5.528%

    No Known Activations