© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 51692
    Prev
    Next
    INDEX
    Explanations

    painting and paint

    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_30_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
    hetamine
    0.39
    Jim
    0.38
     deformity
    0.38
    숑
    0.38
    อดู
    0.37
     সন্ধ্যায়
    0.37
    资产
    0.37
    idelity
    0.36
    .~\
    0.36
    Ошибка
    0.36
    POSITIVE LOGITS
     paint
    0.54
     paints
    0.54
     Paint
    0.51
     पेंट
    0.48
    Paint
    0.45
     벽
    0.44
     PAINT
    0.43
     Paints
    0.43
     peinture
    0.42
     வண்ணப்பூச்சு
    0.41
    Activations Density 0.005%

    No Known Activations