© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 63659
    Prev
    Next
    INDEX
    Explanations

    shirt or shirts

    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_41_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
     fountain
    1.17
     Fountain
    1.04
     fountains
    0.91
     pen
    0.83
    ountain
    0.79
    笔
    0.70
     shirt
    0.69
     pens
    0.68
    筆
    0.67
    Pen
    0.65
    POSITIVE LOGITS
     nDims
    0.42
     spol
    0.42
     öpp
    0.39
    SIDE
    0.39
     Bom
    0.38
     Blocks
    0.38
     terbuka
    0.38
    处置
    0.37
     खुला
    0.36
     открыть
    0.36
    Activations Density 0.011%

    No Known Activations