© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 106887
    Prev
    Next
    INDEX
    Explanations

    wrestle with complexity

    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_2_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
    ش
    2.38
    на
    1.67
    ح
    1.47
     that
    1.45
     to
    1.41
    شون
    1.36
    ن
    1.34
    ш
    1.31
    ج
    1.27
    ری
    1.22
    POSITIVE LOGITS
    (
    1.18
    ޗ
    0.93
    cji
    0.92
    d
    0.92
    Dade
    0.91
    ЕВ
    0.91
    嶈
    0.90
    V
    0.90
    dX
    0.89
     infringing
    0.88
    Activations Density 0.001%

    No Known Activations