© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 11299
    Prev
    Next
    INDEX
    Explanations

    content related to the United States elections and political parties

    oai_token-act-pair · gemini-2.0-flash

    elections and campaigns

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    Autoritní
    -0.75
     صوتيه
    -0.63
    MergeFrom
    -0.62
    ValueStyle
    -0.58
    RACE
    -0.57
    irical
    -0.57
    MigrationBuilder
    -0.57
    LayoutStyle
    -0.56
    race
    -0.56
    baomidou
    -0.56
    POSITIVE LOGITS
     समीक्षक
    0.50
    stock
    0.46
     NPA
    0.44
    STOCK
    0.43
     pernikahan
    0.43
    fortawesome
    0.42
    OfWork
    0.42
     jenner
    0.41
    Stock
    0.41
    Pais
    0.41
    Activations Density 8.237%

    No Known Activations