© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 247388
    Prev
    Next
    INDEX
    Explanations

    libreoffice calc writer

    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_40_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
     utility
    0.44
    籙
    0.43
     lightly
    0.41
     Utility
    0.40
     Locked
    0.39
    utility
    0.39
    appList
    0.39
     lí
    0.38
     Lock
    0.38
    绘画
    0.38
    POSITIVE LOGITS
    mvnrepository
    0.40
    ালের
    0.39
    vidia
    0.39
    칫
    0.36
    springframework
    0.36
    太陽
    0.36
    metter
    0.36
    냇
    0.36
    ProxyAgent
    0.36
    measurable
    0.35
    Activations Density 0.003%

    No Known Activations