© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 176779
    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_20_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
    ກັບ
    0.50
    fare
    0.49
    ເສ
    0.49
    Visiting
    0.47
    㛣
    0.47
    ເຮ
    0.46
    lighting
    0.46
    ເຕ
    0.45
     luminance
    0.45
     pastel
    0.45
    POSITIVE LOGITS
    j
    0.43
     sacred
    0.43
     sheds
    0.42
    ب
    0.41
    ല
    0.41
     Sacred
    0.40
    u
    0.40
    uw
    0.39
     Fundamentals
    0.39
     stedet
    0.39
    Activations Density 0.000%

    No Known Activations