© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 38-GEMMASCOPE-2-TRANSCODER-262K
    4. 266
    Prev
    Next
    INDEX
    Explanations

    color and text color properties

    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_38_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
     हर्षवर्धन
    0.39
    throw
    0.39
    亅
    0.38
    Stylish
    0.37
    淍
    0.37
     Kubo
    0.36
     sever
    0.36
    Throw
    0.35
    ंजनों
    0.35
     rainbows
    0.35
    POSITIVE LOGITS
    textcolor
    0.55
    pressed
    0.52
    TextColor
    0.52
     COLOR
    0.49
     색
    0.47
     Farbe
    0.47
     Color
    0.47
    UIColor
    0.46
     Tint
    0.46
     tint
    0.46
    Activations Density 0.079%

    No Known Activations