© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 1046
    Prev
    Next
    INDEX
    Explanations

    blue color

    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_39_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
     noire
    0.37
     черно
    0.37
     फीस
    0.35
    黑
    0.35
     чор
    0.33
    enez
    0.33
    煞
    0.33
    ێ
    0.33
     ریس
    0.33
     Risks
    0.33
    POSITIVE LOGITS
    Fruit
    0.43
    stehung
    0.39
    green
    0.37
    lime
    0.37
    fruit
    0.36
    lucky
    0.36
    숲
    0.36
     Smoothie
    0.36
     Biografie
    0.36
    ivariate
    0.35
    Activations Density 0.009%

    No Known Activations