© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 232078
    Prev
    Next
    INDEX
    Explanations

    athletes

    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_32_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
     arteries
    0.39
     episcop
    0.38
    ℉
    0.38
    燚
    0.38
    ائص
    0.38
     blister
    0.37
     않는
    0.37
     thermometer
    0.37
    漸
    0.37
     vesc
    0.36
    POSITIVE LOGITS
     سوال
    0.39
     ווי
    0.38
     Demonstrate
    0.38
     Verdi
    0.38
    RootDir
    0.37
     bestaan
    0.37
     questioning
    0.37
    chiha
    0.37
     Absolutely
    0.37
     रोज़
    0.36
    Activations Density 0.001%

    No Known Activations