© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 54831
    Prev
    Next
    INDEX
    Explanations

    hexadecimal color codes

    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_55_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
     yellow
    3.61
     Yellow
    3.55
    黄
    3.55
    Yellow
    3.53
    黃
    3.36
    yellow
    3.23
     YELLOW
    3.19
     жел
    2.98
     황
    2.92
     黄
    2.88
    POSITIVE LOGITS
     Bluetooth
    0.48
     bluetooth
    0.41
    ्रे
    0.38
    鳩
    0.37
    lev
    0.36
     Horton
    0.35
    KSpriteNode
    0.35
    Bluetooth
    0.35
     Unix
    0.35
     पुष्पा
    0.35
    Activations Density 0.009%

    No Known Activations