© 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. 14479
    Prev
    Next
    INDEX
    Explanations

    response status codes

    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
    әү
    0.40
    Or
    0.36
    Alger
    0.35
     Baud
    0.35
    之内
    0.34
    ll
    0.34
    Hydro
    0.33
    ্তা
    0.33
     Orion
    0.33
    ໑
    0.33
    POSITIVE LOGITS
     Fatt
    0.39
    funk
    0.39
     पेड़
    0.39
     पेड़
    0.39
    ப்பிய
    0.38
     கூறியுள்ளார்
    0.38
     कैबिनेट
    0.37
    क्षेप
    0.37
    ffel
    0.37
    ookeeper
    0.37
    Activations Density 0.007%

    No Known Activations