© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-TRANSCODER-262K
    4. 33388
    Prev
    Next
    INDEX
    Explanations

    vibrating paint or light filaments

    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_31_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
    ையுடன்
    0.39
    水を
    0.37
     المرح
    0.36
     الحكومة
    0.36
     政府
    0.36
    叉
    0.36
    printing
    0.35
    黑暗
    0.35
    compart
    0.35
    raving
    0.35
    POSITIVE LOGITS
     overrides
    0.39
    뀔
    0.39
     fluctuations
    0.38
     fluctuation
    0.38
     responsiveness
    0.37
    俪
    0.37
     vying
    0.37
     __________
    0.37
     gamers
    0.36
    鿉
    0.36
    Activations Density 0.065%

    No Known Activations