© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 193163
    Prev
    Next
    INDEX
    Explanations

    fight off

    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_4_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
    ü
    1.05
    使用
    0.93
    기
    0.91
    다
    0.91
    в
    0.84
    어
    0.84
     Société
    0.83
    à
    0.83
    ة
    0.81
    我
    0.81
    POSITIVE LOGITS
    IL
    1.03
    OF
    0.93
    ز
    0.93
    एम
    0.89
    म
    0.89
    \}.
    0.86
    R
    0.85
    ม
    0.85
    pc
    0.83
    OM
    0.82
    Activations Density 0.003%

    No Known Activations