© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 96475
    Prev
    Next
    INDEX
    Explanations

    hutongs (胡同)

    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_14_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
     drink
    0.51
    IG
    0.50
    KW
    0.49
    na
    0.47
     (
    0.46
     hypogly
    0.46
     indium
    0.46
     for
    0.46
     glycerol
    0.45
     glycine
    0.45
    POSITIVE LOGITS
    㖷
    0.55
    萺
    0.54
    堭
    0.54
    墙
    0.53
    恁
    0.50
     mẫu
    0.49
    zustellen
    0.49
    konto
    0.49
    antal
    0.48
    เล่น
    0.47
    Activations Density 0.000%

    No Known Activations