© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 39943
    Prev
    Next
    INDEX
    Explanations

    statistical learning and arbitrage

    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
    Negative Logits
     (
    0.77
    ر
    0.77
    ar
    0.76
    ร
    0.72
    ного
    0.72
    ิ
    0.72
    og
    0.70
    os
    0.67
    ת
    0.67
    ä
    0.65
    POSITIVE LOGITS
     statistique
    0.89
     Estadística
    0.88
    Stat
    0.88
     статисти
    0.87
    Statistical
    0.86
    Statistics
    0.84
     STATISTICS
    0.84
     статистики
    0.83
     statistiques
    0.82
     estadística
    0.82
    Activations Density 0.002%

    No Known Activations