© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 135532
    Prev
    Next
    INDEX
    Explanations

    color names

    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_37_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
     Taylor
    0.39
     খান
    0.38
     Tagen
    0.38
     mill
    0.37
    準
    0.37
     Mill
    0.37
     Qc
    0.37
    BackPressed
    0.36
     Tag
    0.35
    ไม
    0.35
    POSITIVE LOGITS
     color
    0.52
     colored
    0.48
     цвет
    0.47
     রঙের
    0.47
     tints
    0.45
    色の
    0.44
     紫
    0.44
     purple
    0.44
    color
    0.43
     colors
    0.43
    Activations Density 0.000%

    No Known Activations