© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 10939
    Prev
    Next
    INDEX
    Explanations

    enumerations, list items

    oai_token-act-pair · gemini-2.0-flash

    dashes and parentheses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     estekak
    -0.73
     Roskov
    -0.63
     tartalomajánló
    -0.63
    submitted
    -0.60
    Дереккөздер
    -0.58
     contextLoads
    -0.57
    HostException
    -0.56
    VersionUID
    -0.54
     Италијани
    -0.54
    Välislingid
    -0.54
    POSITIVE LOGITS
    Erreferentziak
    0.52
    rmtree
    0.46
    multirow
    0.43
    ută
    0.43
    ArgsConstructor
    0.41
     Erbe
    0.41
    CloseOperation
    0.41
    ocities
    0.40
    nope
    0.40
     Gradually
    0.39
    Activations Density 0.428%

    No Known Activations