© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 10246
    Prev
    Next
    INDEX
    Explanations

    words referring to government, politics, and location.

    oai_token-act-pair · gemini-2.0-flash

    political news

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    ]")]
    -0.97
     للاسماء
    -0.91
     unknownFields
    -0.90
     Efq
    -0.89
     كومونز
    -0.89
    AccessorTable
    -0.85
    berdayakan
    -0.83
    )";
    -0.83
    "):
    -0.82
    .")]
    -0.82
    POSITIVE LOGITS
     in
    0.59
     J
    0.57
     D
    0.53
     [
    0.52
     préciser
    0.50
     non
    0.49
     had
    0.48
    造成的
    0.48
     I
    0.47
     M
    0.47
    Activations Density 1.449%

    No Known Activations