© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 6971
    Prev
    Next
    INDEX
    Explanations

    mentions of groups of people and events

    oai_token-act-pair · gemini-2.0-flash

    women

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     woman
    -0.76
     která
    -0.75
     quelli
    -0.75
     ils
    -0.74
     kurie
    -0.73
     kteří
    -0.73
     którzy
    -0.69
     Woman
    -0.68
     girl
    -0.66
     daughter
    -0.66
    POSITIVE LOGITS
     hero
    0.99
    Elles
    0.73
    hero
    0.72
     Elas
    0.69
    WebElementEntity
    0.65
     Elles
    0.63
     ویکی‌پدیا
    0.63
     Hero
    0.63
     arşivlendi
    0.61
    minton
    0.60
    Activations Density 1.799%

    No Known Activations