© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 248258
    Prev
    Next
    INDEX
    Explanations

    say "punctuation"

    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_56_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :”
    0.41
    Basic
    0.41
    .~\
    0.39
     ঃ
    0.39
    Simulation
    0.38
    冲
    0.38
    ：“
    0.38
    Md
    0.38
    Rush
    0.38
    yld
    0.38
    POSITIVE LOGITS
    如
    0.59
     như
    0.53
    เช่น
    0.52
     como
    0.49
    como
    0.49
     seperti
    0.48
     wie
    0.47
     eg
    0.47
     zoals
    0.47
     जैसे
    0.46
    Activations Density 0.001%

    No Known Activations