© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 84779
    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_0_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
     besonderen
    0.49
    ક્ષા
    0.45
     comuns
    0.45
     kontroll
    0.44
    ان
    0.44
     نص
    0.44
    <unused26>
    0.43
    to
    0.43
    rela
    0.43
    theater
    0.43
    POSITIVE LOGITS
     upcoming
    0.50
     insightful
    0.49
    อยาก
    0.48
    شنامه
    0.47
     sophisticated
    0.47
    JlcG
    0.47
     attached
    0.47
     analysing
    0.47
    データ
    0.47
    izowane
    0.47
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.