© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 11730
    Prev
    Next
    INDEX
    Explanations

    motivation and encouragement

    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_13_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
    م
    0.58
    к
    0.54
    лю
    0.50
    ক
    0.50
    क
    0.49
    м
    0.48
    iesa
    0.48
    ングラス
    0.47
     debugShow
    0.47
     overlays
    0.47
    POSITIVE LOGITS
    a
    0.57
    force
    0.57
     cinq
    0.57
     furnace
    0.54
     সাহস
    0.54
    Elastic
    0.54
     encouragement
    0.52
     *
    0.52
    ับสนุน
    0.52
     বিধি
    0.51
    Activations Density 0.075%

    No Known Activations