© 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. 36962
    Prev
    Next
    INDEX
    Explanations

    new classes and instances

    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
     সমূহ
    0.40
     याबाबत
    0.40
    achy
    0.38
    𝘺
    0.38
     Überblick
    0.37
    ഞ്ഞി
    0.36
    唵
    0.36
    ussy
    0.36
     sickle
    0.35
    苗
    0.35
    POSITIVE LOGITS
     goes
    0.40
     calls
    0.39
    goes
    0.38
     pol
    0.37
     количеством
    0.36
    Pent
    0.36
     stall
    0.35
     llama
    0.35
    Pol
    0.35
    再加上
    0.34
    Activations Density 0.002%

    No Known Activations