© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 168700
    Prev
    Next
    INDEX
    Explanations

    matching resource

    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_34_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
     huy
    0.41
     cardinals
    0.38
    bley
    0.37
    疲れ
    0.36
     मारे
    0.35
    めで
    0.35
     Sask
    0.34
     चर्चित
    0.34
    捙
    0.34
    وتي
    0.34
    POSITIVE LOGITS
     образа
    0.38
    gaxModule
    0.38
    lam
    0.38
     arguments
    0.37
     Listing
    0.36
    iodate
    0.35
     Lam
    0.34
    ┐
    0.34
     lam
    0.34
     Imaging
    0.34
    Activations Density 0.003%

    No Known Activations