© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 32806
    Prev
    Next
    INDEX
    Explanations

    white

    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
     black
    1.30
    Black
    1.21
     Black
    1.19
    black
    1.15
    黑
    1.15
    黒
    1.09
     BLACK
    1.09
    BLACK
    1.07
     블랙
    1.07
    ブラック
    1.06
    POSITIVE LOGITS
     white
    1.91
    white
    1.73
     White
    1.70
    白
    1.66
     WHITE
    1.64
    White
    1.63
    WHITE
    1.61
     beyaz
    1.52
     белый
    1.47
     putih
    1.42
    Activations Density 0.063%

    No Known Activations