© 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. 3920
    Prev
    Next
    INDEX
    Explanations

    legal documents and court proceedings

    oai_token-act-pair · gemini-2.0-flash

    dates and court filings

    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
     kasarigan
    -0.56
    ViewFeatures
    -0.53
    ENDIF
    -0.50
    mator
    -0.49
    útbol
    -0.45
    []):
    -0.45
     silo
    -0.44
    ernoo
    -0.44
    INTEN
    -0.43
    FieldNumber
    -0.43
    POSITIVE LOGITS
    WebServlet
    0.75
     disambiguazione
    0.70
     متعلقه
    0.67
    GenerationType
    0.63
     DataTypes
    0.62
    makeConstraints
    0.60
    expandindo
    0.57
     Winaray
    0.56
    AxisAlignment
    0.55
    ollectionView
    0.53
    Activations Density 0.392%

    No Known Activations