© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 199972
    Prev
    Next
    INDEX
    Explanations

    blade in the dark scenario

    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_15_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
     ধর্ম
    0.56
     falleció
    0.55
    )):
    0.54
    ные
    0.54
     mortality
    0.53
    /</
    0.53
    )</
    0.52
     е
    0.51
     mildew
    0.51
    Бу
    0.50
    POSITIVE LOGITS
     ڈیٹ
    0.57
    웍
    0.54
    wString
    0.52
     கட்சியின்
    0.52
     kay
    0.52
     ジャ
    0.52
    ⟥
    0.52
    文字列
    0.51
     Writ
    0.48
    onin
    0.47
    Activations Density 0.003%

    No Known Activations