© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 128953
    Prev
    Next
    INDEX
    Explanations

    Ghent, Graz

    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_6_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
    К
    0.93
    После
    0.90
    お金
    0.87
    はじめ
    0.86
     acestea
    0.86
    Ч
    0.85
    Ф
    0.82
     порядок
    0.82
    例えば
    0.81
     вклад
    0.81
    POSITIVE LOGITS
    ä
    1.09
    7
    1.02
     as
    0.94
    }
    0.92
    و
    0.92
     with
    0.88
    َ
    0.83
    มัน
    0.82
    á
    0.82
    ')
    0.82
    Activations Density 0.000%

    No Known Activations