© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 96364
    Prev
    Next
    INDEX
    Explanations

    graphics rendering context

    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_14_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
     Juin
    0.61
     Reykjavik
    0.57
     Who
    0.56
     primi
    0.56
     лиц
    0.53
     Inventors
    0.52
    
    0.50
     Apartment
    0.50
     Step
    0.49
     这
    0.49
    POSITIVE LOGITS
    hr
    0.58
    gz
    0.58
    i
    0.55
    gebras
    0.54
     algebras
    0.54
    Nil
    0.52
    them
    0.51
    ague
    0.50
    guna
    0.50
    书籍
    0.50
    Activations Density 0.002%

    No Known Activations