© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 205302
    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_10_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
    ng
    0.54
    ngl
    0.52
    imageList
    0.49
    ths
    0.48
    Щ
    0.48
    Пе
    0.47
     angulis
    0.47
    З
    0.46
    t
    0.46
     claimants
    0.45
    POSITIVE LOGITS
    ोदय
    0.52
    ו
    0.50
    ेद
    0.47
    ท้าย
    0.47
    л
    0.46
     desarrollar
    0.46
     sassy
    0.45
     Raspberry
    0.44
     trunk
    0.44
     deterrent
    0.44
    Activations Density 0.000%

    No Known Activations