© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 212788
    Prev
    Next
    INDEX
    Explanations

    Ga/Gao sounds

    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_50_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Jia
    1.02
    jia
    0.91
    贾
    0.79
    甲
    0.75
    JA
    0.74
     Jah
    0.73
    賈
    0.72
     ji
    0.69
     Ji
    0.68
     jah
    0.68
    POSITIVE LOGITS
     Ga
    1.13
    Ga
    1.04
     ga
    1.00
     Gao
    0.97
    ga
    0.83
     Gauss
    0.78
     GAO
    0.78
     GA
    0.74
     Gael
    0.72
     gauss
    0.72
    Activations Density 0.037%

    No Known Activations