© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 194096
    Prev
    Next
    INDEX
    Explanations

    flash mode or effect

    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_9_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
     increases
    0.62
     TextView
    0.60
     accusations
    0.60
     rutas
    0.60
     lawsuits
    0.59
    د
    0.59
     faucets
    0.58
     breakthroughs
    0.57
     Complaints
    0.57
     algebra
    0.56
    POSITIVE LOGITS
    ge
    0.72
    -
    0.70
    ro
    0.66
    ut
    0.64
    lor
    0.63
    ah
    0.62
    ada
    0.62
    anya
    0.61
    ında
    0.59
    igen
    0.59
    Activations Density 0.000%

    No Known Activations