© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 67333
    Prev
    Next
    INDEX
    Explanations

    grayscale or shades of gray

    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_41_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
     W
    0.53
     Japanese
    0.50
    W
    0.47
     япон
    0.46
     w
    0.45
     k
    0.45
     K
    0.42
    일본
    0.41
     জাপ
    0.41
     japonais
    0.40
    POSITIVE LOGITS
     gray
    1.10
     grayscale
    1.07
    grayscale
    1.02
     gre
    0.98
     Gray
    0.93
    gray
    0.93
     GRAY
    0.93
     grey
    0.91
    灰
    0.90
    Gray
    0.88
    Activations Density 0.008%

    No Known Activations