© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 64096
    Prev
    Next
    INDEX
    Explanations

    Swift

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
     swift
    2.30
    swift
    1.91
     speedy
    1.82
     Swift
    1.80
    Swift
    1.79
     Speedy
    1.43
     swiftly
    1.05
     %@
    1.03
     %@",
    1.01
    %@",
    0.94
    POSITIVE LOGITS
     sv
    0.52
    sv
    0.43
     Sv
    0.41
    Sv
    0.41
     glo
    0.37
     Pom
    0.37
     tvr
    0.36
    svn
    0.35
    hoven
    0.35
     aliquot
    0.35
    Activations Density 0.021%

    No Known Activations