© 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-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 87121
    Prev
    Next
    INDEX
    Explanations

    squad leaders

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_3_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ิ
    0.84
    em
    0.82
    的多
    0.68
    "
    0.62
    ot
    0.61
    었고
    0.61
    ె
    0.61
     Transactions
    0.59
     письмо
    0.59
    ract
    0.58
    POSITIVE LOGITS
    Y
    0.95
    AL
    0.79
    IS
    0.73
    IR
    0.73
    I
    0.69
    RO
    0.68
    ICK
    0.68
     dampen
    0.66
    ك
    0.66
    IO
    0.66
    Activations Density 0.000%

    No Known Activations