© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 170325
    Prev
    Next
    INDEX
    Explanations

    can help explain generate write code

    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_20_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
     (#
    0.37
    ؛
    0.34
     Panels
    0.33
    Walls
    0.33
    ailand
    0.32
    ۔
    0.32
    /#
    0.32
    туга
    0.31
    Panel
    0.31
    】,
    0.31
    POSITIVE LOGITS
     pâte
    0.35
     Adolf
    0.34
     रोजगार
    0.34
    artifact
    0.32
     राजकुमार
    0.32
    场合
    0.32
     آثار
    0.31
    성이
    0.31
     성
    0.30
    도의
    0.30
    Activations Density 0.020%

    No Known Activations