© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 21775
    Prev
    Next
    INDEX
    Explanations

    color

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     Copp
    0.38
    irre
    0.37
    花了
    0.36
    badbreak
    0.35
    花
    0.35
    quick
    0.35
     Bred
    0.35
    pers
    0.35
    的花
    0.34
    )^{(
    0.34
    POSITIVE LOGITS
     color
    2.39
     colour
    2.22
    色
    2.20
    color
    2.08
     цвет
    2.08
     colors
    2.05
     Color
    2.02
    Color
    1.93
     색
    1.93
     COLOR
    1.90
    Activations Density 0.008%

    No Known Activations