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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 1166
    Prev
    Next
    INDEX
    Explanations

    instances of hunting, specifically with bows and arrows

    oai_token-act-pair · gemini-2.0-flash

    bows and arrows/bowing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     BOW
    -1.84
     bow
    -1.80
     Bow
    -1.79
    Bow
    -1.77
    bow
    -1.71
     arrow
    -1.65
    BOW
    -1.65
     Arrow
    -1.57
     arrows
    -1.54
     bows
    -1.54
    POSITIVE LOGITS
     Stedman
    0.49
    haba
    0.47
     Chatter
    0.45
     Cypri
    0.45
     Hager
    0.44
    パク
    0.44
    hasData
    0.43
    vičius
    0.41
    Läs
    0.41
     Habib
    0.41
    Activations Density 1.840%

    No Known Activations