© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 48350
    Prev
    Next
    INDEX
    Explanations

    deactivation, disabled, inactive

    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_31_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
     baseX
    0.40
    ArgumentParser
    0.39
    urunan
    0.38
    ाई
    0.37
    PLEX
    0.37
    binghamton
    0.36
    蒇
    0.36
    杼
    0.36
    莠
    0.36
    आईटी
    0.36
    POSITIVE LOGITS
    DISABLED
    0.49
     disable
    0.47
     disabled
    0.46
     invalidated
    0.45
     Disabled
    0.45
     diagonally
    0.44
     diagonal
    0.44
    Disabled
    0.43
    Bloomberg
    0.43
    disabled
    0.42
    Activations Density 0.088%

    No Known Activations