© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 24965
    Prev
    Next
    INDEX
    Explanations

    STAT

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     мі
    1.98
    ミ
    1.98
     ми
    1.97
     Mi
    1.97
     MI
    1.95
     mi
    1.92
     Ми
    1.91
     mí
    1.88
    Mi
    1.83
     miRNA
    1.81
    POSITIVE LOGITS
    STAT
    0.48
     STAT
    0.48
     Stat
    0.46
    stat
    0.46
     stat
    0.45
    Stat
    0.45
     स्टैट
    0.40
     статисти
    0.38
     Estat
    0.36
     PHILLIPS
    0.36
    Activations Density 0.006%

    No Known Activations