© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 198996
    Prev
    Next
    INDEX
    Explanations

    response explained

    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_4_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
    ز
    1.33
    να
    1.09
    ف
    1.02
    تر
    0.98
    ر
    0.95
    ut
    0.95
    р
    0.94
    ме
    0.93
    ap
    0.93
    са
    0.92
    POSITIVE LOGITS
    t
    1.10
    5
    0.87
    2
    0.86
     I
    0.86
     didn
    0.82
    IER
    0.81
    JA
    0.80
    _
    0.79
    ITE
    0.78
    I
    0.77
    Activations Density 0.028%

    No Known Activations