© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 257193
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_22_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
     Такой
    0.48
     రాజకీయ
    0.47
     डॉक्ट
    0.46
     ያላቸው
    0.46
    ă
    0.46
    ations
    0.45
    enta
    0.44
     பகு
    0.44
     Politics
    0.44
     ስርዓ
    0.44
    POSITIVE LOGITS
    thread
    0.52
    می
    0.50
    question
    0.50
    んでも
    0.47
    tipo
    0.46
    ޒ
    0.45
    د
    0.44
     easily
    0.43
    се
    0.42
     facilmente
    0.42
    Activations Density 0.000%

    No Known Activations