© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 8867
    Prev
    Next
    INDEX
    Explanations

    legal citations, especially those including U.S. Supreme Court cases, and/or references to polling data related to presidential approval ratings.

    oai_token-act-pair · gemini-2.0-flash

    US legal, historical contexts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    CloseOperation
    -0.81
     betweenstory
    -0.75
     становника
    -0.73
    migrationBuilder
    -0.72
     autorytatywna
    -0.69
    ThroughAttribute
    -0.63
    Билгалдахарш
    -0.61
    RunWith
    -0.60
     QtGui
    -0.59
    modelBuilder
    -0.59
    POSITIVE LOGITS
    nis
    0.51
     Nixon
    0.51
     cajas
    0.50
    quisa
    0.48
    tagext
    0.47
    retanto
    0.45
     editados
    0.44
    тан
    0.44
     opge
    0.43
     compréhen
    0.43
    Activations Density 1.773%

    No Known Activations