© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    4. 164734
    Prev
    Next
    INDEX
    Explanations

    Rex, Wars, Echo, Lux

    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
    되면
    0.50
    ალური
    0.48
    HDL
    0.48
    ดับ
    0.47
    َه
    0.47
    ListView
    0.46
    ене
    0.45
    깁
    0.45
    けば
    0.44
    Hydrochloride
    0.43
    POSITIVE LOGITS
    /
    0.59
     ដ
    0.58
    ezi
    0.55
    ate
    0.54
     приложений
    0.53
     xứ
    0.52
     Himal
    0.52
     ți
    0.52
     країн
    0.51
    ee
    0.51
    Activations Density 0.001%

    No Known Activations