© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 4234
    Prev
    Next
    INDEX
    Explanations

    venue and performance locations

    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_40_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
     picnics
    0.39
     කෙ
    0.38
     Voit
    0.37
     сбор
    0.37
     Hobby
    0.36
     Clearing
    0.36
     कंड
    0.36
    rire
    0.35
    뱀
    0.35
     Free
    0.35
    POSITIVE LOGITS
     venues
    1.23
     venue
    1.19
     spaces
    1.06
    Venue
    1.05
    spaces
    0.94
     Venue
    0.94
    venue
    0.93
     espaços
    0.93
     espacios
    0.91
    venues
    0.88
    Activations Density 0.061%

    No Known Activations