© 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. 145709
    Prev
    Next
    INDEX
    Explanations

    concepts

    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
    Not in Any Lists

    No Comments

    Negative Logits
     theoret
    0.52
     theoretical
    0.45
    theoretical
    0.38
     Theoretical
    0.38
    ility
    0.37
    Theoretical
    0.37
    ัง
    0.36
    ✯
    0.36
     وآ
    0.35
     giocatori
    0.35
    POSITIVE LOGITS
     humor
    0.54
     Humor
    0.50
     humour
    0.46
     litt
    0.44
     religion
    0.38
    Hum
    0.38
    Soy
    0.37
     fab
    0.36
    Moral
    0.36
     Encycl
    0.35
    Activations Density 0.003%

    No Known Activations