© 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. 16332
    Prev
    Next
    INDEX
    Explanations

    beautiful or ugly descriptions

    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
     सकारात्मक
    0.36
     stork
    0.34
    urb
    0.33
     positivas
    0.33
     simd
    0.33
     அடுக்கு
    0.33
     Maver
    0.32
    ുണ്ട്
    0.32
    ቫ
    0.32
    メリット
    0.32
    POSITIVE LOGITS
    Lighting
    0.32
    Shawn
    0.32
     Led
    0.32
     lighting
    0.31
    Cow
    0.31
    Flash
    0.31
    Led
    0.31
    GED
    0.31
    照明
    0.31
    colors
    0.30
    Activations Density 0.006%

    No Known Activations