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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 28177
    Prev
    Next
    INDEX
    Explanations

    .font() with font styles

    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
    linked
    0.43
    tag
    0.40
    (@
    0.40
     linked
    0.39
     запро
    0.38
    fromParams
    0.37
    सादर
    0.37
    ⓧ
    0.37
     #${
    0.36
    她在
    0.36
    POSITIVE LOGITS
    geom
    0.42
    juv
    0.40
     시스템
    0.39
     besitzen
    0.39
     অ্যাপ
    0.39
     系统
    0.39
    カバー
    0.38
    系统
    0.38
     Void
    0.38
    ihu
    0.37
    Activations Density 0.001%

    No Known Activations