© 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. 151849
    Prev
    Next
    INDEX
    Explanations

    a

    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
     a
    0.56
    A
    0.48
    a
    0.46
    Special
    0.42
    ！
    0.42
    Take
    0.41
    THANK
    0.40
    VERY
    0.39
     feedback
    0.39
    ![
    0.39
    POSITIVE LOGITS
     massive
    0.56
     Copy
    0.53
     Massive
    0.53
     copy
    0.51
    massive
    0.50
     massively
    0.49
     Kop
    0.44
     Mass
    0.42
    copy
    0.41
     कॉपी
    0.40
    Activations Density 0.001%

    No Known Activations