© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 44025
    Prev
    Next
    INDEX
    Explanations

    hello "world" / brushes / habits

    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_3_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
    sch
    0.80
    l
    0.71
    nın
    0.70
    n
    0.70
    ل
    0.70
    ৪
    0.68
     Ladakh
    0.68
     był
    0.67
     byl
    0.67
    ак
    0.66
    POSITIVE LOGITS
    ס
    0.85
    ,
    0.73
     불구하고
    0.63
    Verified
    0.59
    aj
    0.58
    前进
    0.58
    ued
    0.57
    sembles
    0.57
    สต์
    0.57
    sembled
    0.56
    Activations Density 0.010%

    No Known Activations