© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 29967
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_7_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
    0.85
    ↵↵
    0.55
     countenance
    0.54
    ล
    0.52
     hemisph
    0.50
     Bob
    0.50
     portions
    0.50
     antenna
    0.49
     sta
    0.49
     dome
    0.49
    POSITIVE LOGITS
    ut
    0.59
    t
    0.57
    g
    0.55
    ين
    0.54
    setminus
    0.54
     ব্যাকটেরিয়া
    0.54
    There
    0.53
    efficacité
    0.53
    Reactive
    0.52
    cemia
    0.52
    Activations Density 0.000%

    No Known Activations