© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 45309
    Prev
    Next
    INDEX
    Explanations

    official / officials

    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_10_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
    ق
    0.21
    ad
    0.19
    س
    0.19
     アイス
    0.17
    $
    0.17
    ed
    0.16
     Cyborg
    0.16
     Boats
    0.16
     आतंकवाद
    0.16
    ポーター
    0.16
    POSITIVE LOGITS
    и
    0.26
    و
    0.24
    larını
    0.23
    l
    0.23
    ያንዳ
    0.21
     novos
    0.21
    ной
    0.20
    larının
    0.20
    tai
    0.20
    theit
    0.20
    Activations Density 0.003%

    No Known Activations