© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 40517
    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_57_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
    alten
    0.41
     объеди
    0.39
    টেলে
    0.38
    を加
    0.36
     эр
    0.36
    スペシャル
    0.35
    ленными
    0.34
     detenido
    0.34
    commitment
    0.34
    溲
    0.34
    POSITIVE LOGITS
    ..
    0.37
     dur
    0.37
     read
    0.36
     against
    0.36
     이러한
    0.35
     near
    0.34
     ..
    0.34
     segment
    0.34
     generally
    0.34
     happened
    0.34
    Activations Density 0.000%

    No Known Activations