© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12204
    Prev
    Next
    INDEX
    Explanations

    words relating to government, politics, law, and bureaucracy

    oai_token-act-pair · gemini-2.0-flash

    legal and governmental contexts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     дописавши
    -0.80
     Italijanski
    -0.79
     doubtnut
    -0.77
    ThroughAttribute
    -0.75
     Forder
    -0.73
     Reverso
    -0.73
     intStringLen
    -0.73
    :][
    -0.71
    parsedMessage
    -0.70
     raiſ
    -0.69
    POSITIVE LOGITS
     office
    0.65
     department
    0.60
     Department
    0.60
     Office
    0.57
     authority
    0.54
     Authority
    0.54
     Directorate
    0.53
     Bureau
    0.52
     offices
    0.48
     managing
    0.47
    Activations Density 0.468%

    No Known Activations