© 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. 6248
    Prev
    Next
    INDEX
    Explanations

    words related to legal documents and evidence

    oai_token-act-pair · gemini-2.0-flash

    Legal/financial documents

    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
    errHandler
    -0.55
     Adrian
    -0.46
    R
    -0.46
     amantes
    -0.45
    立ち
    -0.45
     umum
    -0.44
    anzo
    -0.44
    ana
    -0.44
    chauer
    -0.43
    šta
    -0.43
    POSITIVE LOGITS
     FetchType
    0.89
    AnimationsModule
    0.87
     ExecuteAsync
    0.82
    bootstrapcdn
    0.79
    InjectAttribute
    0.77
    XmlAccessType
    0.73
    NgModule
    0.73
    complexContent
    0.66
    migrationBuilder
    0.66
    RepeatedField
    0.66
    Activations Density 2.227%

    No Known Activations