© 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. 54434
    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
     短
    0.42
    イギリス
    0.42
    短
    0.41
     Short
    0.41
    short
    0.41
     short
    0.39
    Short
    0.39
     짧
    0.39
     இறை
    0.39
     SHORT
    0.39
    POSITIVE LOGITS
     ?>">
    0.36
     Грузии
    0.35
     brains
    0.33
     Polygon
    0.33
    brains
    0.32
    ImportGroup
    0.32
     Ска
    0.32
    Subscribe
    0.31
     Cuban
    0.30
     parac
    0.30
    Activations Density 0.000%

    No Known Activations