© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 4728
    Prev
    Next
    INDEX
    Explanations

    geopolitical and U.S. political terms, especially those involving conflict and power.

    oai_token-act-pair · gemini-2.0-flash

    Politics and leaving (pulling out)

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     للمعارف
    -0.58
    IMPORTED
    -0.55
    principalColumn
    -0.54
    UnsafeEnabled
    -0.54
    twimg
    -0.53
    AxisAlignment
    -0.53
    NSIndexPath
    -0.50
     Mérimée
    -0.50
     GlobalKey
    -0.50
     LUMP
    -0.49
    POSITIVE LOGITS
    MigrationBuilder
    0.63
    ValueStyle
    0.62
     مشين
    0.58
    +][
    0.56
     Réponses
    0.54
    ريقيا
    0.54
     CANCEL
    0.51
    abandoned
    0.50
    PyTuple
    0.50
    IBarButtonItem
    0.49
    Activations Density 1.913%

    No Known Activations