© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 13476
    Prev
    Next
    INDEX
    Explanations

    test code snippets

    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_15_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
    は
    0.55
    可以在
    0.54
     can
    0.52
     psychology
    0.50
    ote
    0.49
     balloons
    0.49
    È
    0.49
     is
    0.49
    omorphism
    0.48
    is
    0.48
    POSITIVE LOGITS
     hiz
    0.59
     партия
    0.57
     них
    0.56
     instructive
    0.56
     ထ
    0.55
     ପ
    0.55
     رسول
    0.54
     желе
    0.54
    евич
    0.54
     HUOBI
    0.54
    Activations Density 0.001%

    No Known Activations