© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 12768
    Prev
    Next
    INDEX
    Explanations

    mentions of "he" and "she" in close proximity

    oai_token-act-pair · gemini-2.0-flash

    he

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     he
    -3.69
     он
    -2.03
    he
    -1.60
     він
    -1.56
     그는
    -1.55
    그는
    -1.53
     הוא
    -1.31
    他
    -1.28
    He
    -1.27
    彼は
    -1.27
    POSITIVE LOGITS
     them
    0.75
    I
    0.73
    (
    0.68
    them
    0.63
    ↵↵
    0.60
    .
    0.60
    i
    0.58
    ↵
    0.56
    a
    0.56
    {
    0.55
    Activations Density 1.091%

    No Known Activations