© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 85255
    Prev
    Next
    INDEX
    Explanations

    Supermassive Black Holes

    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_3_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
    ר
    1.00
    ر
    0.97
    ਰ
    0.81
    CS
    0.80
    కర
    0.70
     complète
    0.64
    ئي
    0.64
     recommandée
    0.64
    רק
    0.64
    SC
    0.63
    POSITIVE LOGITS
     व
    0.66
    k
    0.57
     explanatory
    0.56
     своє
    0.56
    kommen
    0.56
    ם
    0.56
     כ
    0.55
     و
    0.55
    ก
    0.55
     कौन
    0.54
    Activations Density 0.003%

    No Known Activations