© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 60
    Prev
    Next
    INDEX
    Explanations

    words or phrases relating to elections and political processes

    oai_token-act-pair · gemini-2.0-flash

    voters

    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
    WebServlet
    -0.56
     faisons
    -0.50
    basicConfig
    -0.48
    ROUTINE
    -0.47
     Réponses
    -0.44
     tavolo
    -0.44
    πού
    -0.43
    ryu
    -0.43
     bewe
    -0.42
    TouchListener
    -0.42
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.67
     ModelExpression
    0.67
    ########.
    0.62
    $_['
    0.62
     незавершена
    0.60
    Derbyniad
    0.59
    xnn
    0.59
    featureID
    0.58
     Marat
    0.57
    queryInterface
    0.57
    Activations Density 2.195%

    No Known Activations