© 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. 205749
    Prev
    Next
    INDEX
    Explanations

    publicly available information

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Parking
    0.54
    Parking
    0.49
    Sprint
    0.47
    Rating
    0.44
    Security
    0.44
    Egg
    0.44
    
    0.43
    Traffic
    0.43
     xyz
    0.42
     parking
    0.42
    POSITIVE LOGITS
    先日
    0.49
    gewicht
    0.48
    ​—
    0.47
    fib
    0.47
     ಹೇಳಿದರು
    0.46
     chiều
    0.45
    commission
    0.45
     ತಿಳಿದ
    0.45
     दावा
    0.44
     ನೋಡ
    0.44
    Activations Density 0.001%

    No Known Activations