© 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. 2438
    Prev
    Next
    INDEX
    Explanations

    drawing and art creation

    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
    ljed
    0.41
     기대
    0.40
     Portland
    0.39
    長い
    0.39
    ^*(\
    0.39
     PC
    0.38
    цыю
    0.38
    ాప
    0.37
     कैप
    0.36
     Houston
    0.36
    POSITIVE LOGITS
     vẽ
    0.55
     drawing
    0.54
    Drawing
    0.52
    绘制
    0.52
     drawings
    0.50
    绘
    0.50
     dibuj
    0.48
     Drawings
    0.47
     disegnare
    0.47
     sketching
    0.46
    Activations Density 0.000%

    No Known Activations