© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 59030
    Prev
    Next
    INDEX
    Explanations

    fright, lore, bowel, brave, clubs

    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_2_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
    ного
    1.29
     categor
    1.16
    м
    1.10
     neoplasms
    1.04
    ди
    1.01
     renormal
    1.00
    lad
    0.97
     цене
    0.97
    га
    0.95
    см
    0.95
    POSITIVE LOGITS
    א
    1.09
    ها
    1.04
    ty
    1.03
    al
    1.01
    ية
    1.01
    ai
    0.95
    자
    0.92
    什么
    0.91
    od
    0.89
    ли
    0.89
    Activations Density 0.000%

    No Known Activations