© 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. 81249
    Prev
    Next
    INDEX
    Explanations

    good starting point

    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
     dom
    0.39
    mare
    0.37
     pomoći
    0.34
     هنر
    0.34
     mimics
    0.34
     aimer
    0.33
     田
    0.33
    ilfe
    0.32
    献
    0.32
    TM
    0.32
    POSITIVE LOGITS
     શરૂ
    0.44
     ആരംഭ
    0.38
     уско
    0.37
     آغاز
    0.35
     начала
    0.34
    пера
    0.33
     আরম্ভ
    0.33
    isDirectory
    0.33
     Украї
    0.33
     здания
    0.33
    Activations Density 0.003%

    No Known Activations