© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 195431
    Prev
    Next
    INDEX
    Explanations

    hooves

    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_4_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
     on
    0.57
    ේ
    0.54
     commotion
    0.51
    ુ
    0.49
    يف
    0.49
    د
    0.49
    ς
    0.49
    ER
    0.48
     njegov
    0.48
     kaleidoscopic
    0.48
    POSITIVE LOGITS
    v
    0.60
    1
    0.60
    hong
    0.55
    را
    0.54
    ;
    0.54
    ,
    0.54
    ।
    0.53
    ار
    0.52
    ྰ
    0.51
    to
    0.50
    Activations Density 0.001%

    No Known Activations