© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13177
    Prev
    Next
    INDEX
    Explanations

    sentences that discuss making choices based on beliefs, values, or consequences.

    oai_token-act-pair · gemini-2.0-flash

    decision

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    HtmlAttribute
    -0.60
    cline
    -0.53
    RuleContext
    -0.52
    NOPQRST
    -0.50
    eeq
    -0.48
     Werden
    -0.46
    Violation
    -0.45
    スラ
    -0.44
     Shukla
    -0.43
    ercicio
    -0.43
    POSITIVE LOGITS
     decision
    0.92
     decisions
    0.83
    cision
    0.82
     deci
    0.80
    decision
    0.79
    DECISION
    0.77
     choices
    0.75
    Dec
    0.75
    choices
    0.74
    decisions
    0.73
    Activations Density 1.019%

    No Known Activations