© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 129165
    Prev
    Next
    INDEX
    Explanations

    mistake

    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_1_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
    4
    1.00
    ز
    0.99
    ص
    0.94
    3
    0.93
    ur
    0.92
    ,
    0.91
    8
    0.91
    K
    0.90
    ↵↵
    0.89
    AR
    0.88
    POSITIVE LOGITS
     can
    1.12
    a
    1.08
     has
    0.96
    ה
    0.86
    した
    0.82
     currents
    0.77
     ו
    0.76
     brains
    0.75
     connexes
    0.74
    𝗮
    0.73
    Activations Density 0.001%

    No Known Activations