© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 10153
    Prev
    Next
    INDEX
    Explanations

    artificial coloring and dyes

    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_40_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
    Walt
    0.43
    bli
    0.39
     Walt
    0.39
    겸
    0.37
    తు
    0.35
    可见
    0.35
     কাক
    0.35
    ển
    0.34
    ジュール
    0.34
    푹
    0.34
    POSITIVE LOGITS
     coloring
    1.27
    coloring
    1.16
     colouring
    1.13
     Coloring
    1.08
     dyes
    1.05
     dye
    0.99
    色素
    0.99
     flavoring
    0.90
     Dye
    0.89
     artificial
    0.87
    Activations Density 0.047%

    No Known Activations