© 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. 81132
    Prev
    Next
    INDEX
    Explanations

    notes

    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_31_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
     divergence
    0.39
     स्वर
    0.37
     diverges
    0.36
     ৃ
    0.36
     интересу
    0.35
    
    0.34
    ímav
    0.34
    呤
    0.34
     ની
    0.33
    菣
    0.33
    POSITIVE LOGITS
    pressure
    0.31
     nominal
    0.30
    market
    0.30
    seat
    0.30
    slag
    0.30
    surprise
    0.30
    िल्ली
    0.29
    orderEntry
    0.29
    grand
    0.29
    leb
    0.29
    Activations Density 0.003%

    No Known Activations