© 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. 63530
    Prev
    Next
    INDEX
    Explanations

    K-wire, wire materials, wire services

    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
    ാൽ
    0.39
    Rug
    0.39
     bölün
    0.38
     पेड़
    0.37
     متحده
    0.37
    icin
    0.36
    Sant
    0.36
    冊
    0.36
     musk
    0.35
    ႁ
    0.35
    POSITIVE LOGITS
     wire
    2.17
     wires
    1.93
     Wire
    1.88
    wire
    1.86
    Wire
    1.77
    wires
    1.64
    Wires
    1.48
     WIRE
    1.48
     wiring
    1.39
     wired
    1.38
    Activations Density 0.013%

    No Known Activations