© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 81059
    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_31_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    詑
    0.41
     ow
    0.40
    কেন্ড
    0.39
     époque
    0.39
     mischief
    0.39
    xception
    0.38
    க்கெ
    0.38
    小数
    0.37
    rals
    0.37
    Timeline
    0.37
    POSITIVE LOGITS
    $.)
    0.52
    freeze
    0.42
     slab
    0.39
    गरी
    0.38
     Сергея
    0.38
     forgot
    0.37
    versammlung
    0.37
    forgot
    0.37
    வக
    0.37
    ignore
    0.36
    Activations Density 0.000%

    No Known Activations