© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 6957
    Prev
    Next
    INDEX
    Explanations

    font-family: sans-serif

    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
    Not in Any Lists

    No Comments

    Negative Logits
    撑
    0.39
     ROH
    0.39
    烈
    0.38
     Roj
    0.38
     Rudolph
    0.37
    సులు
    0.36
    撐
    0.36
    ichiro
    0.36
    課
    0.36
     stoichi
    0.36
    POSITIVE LOGITS
     font
    2.39
    font
    2.13
    Font
    2.08
     Font
    2.05
     fonts
    2.03
    字体
    1.88
    FONT
    1.70
     шрифт
    1.66
     шриф
    1.66
     Fonts
    1.65
    Activations Density 0.027%

    No Known Activations