© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 26594
    Prev
    Next
    INDEX
    Explanations

    is

    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_10_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
    ।
    0.77
    n
    0.73
    et
    0.69
     of
    0.62
     you
    0.61
    ל
    0.61
     (
    0.60
    x
    0.57
      
    0.56
    you
    0.54
    POSITIVE LOGITS
    ０
    0.70
    գ
    0.62
     படங்கள்
    0.60
     lados
    0.59
    ваний
    0.58
    м
    0.57
    га
    0.56
    其他
    0.56
     míst
    0.56
    وں
    0.56
    Activations Density 0.170%

    No Known Activations