© 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. 63558
    Prev
    Next
    INDEX
    Explanations

    yarn and wool crafts

    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
     policym
    0.39
    viat
    0.38
     정책
    0.38
    fertigt
    0.38
     ткань
    0.38
    殮
    0.37
     ব্যক্তিত্ব
    0.37
    伸手
    0.37
     fabrics
    0.37
     тексти
    0.37
    POSITIVE LOGITS
     yarn
    1.16
     Yarn
    1.07
     yarns
    1.01
    yarn
    0.93
     ske
    0.52
     sợi
    0.51
     garn
    0.49
     Garn
    0.48
     ball
    0.46
    糸
    0.45
    Activations Density 0.001%

    No Known Activations