© 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. 41556
    Prev
    Next
    INDEX
    Explanations

    man named

    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
    니다
    0.76
    '
    0.67
    기
    0.66
    ↵↵
    0.65
    digital
    0.64
     สาว
    0.64
     istek
    0.64
     to
    0.64
     이유
    0.63
    ない
    0.62
    POSITIVE LOGITS
    1.17
    و
    0.90
    ug
    0.78
    é
    0.78
    ي
    0.73
    ،
    0.73
    ু
    0.72
    س
    0.71
    It
    0.69
     It
    0.68
    Activations Density 0.003%

    No Known Activations