© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 123783
    Prev
    Next
    INDEX
    Explanations

    lavish, lavash

    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
    ৬
    0.73
    म
    0.69
    ियों
    0.68
    లుగా
    0.68
    ب
    0.68
    मल
    0.67
    ahar
    0.66
     이야기를
    0.65
    ukov
    0.65
    ен
    0.64
    POSITIVE LOGITS
     في
    0.72
     в
    0.64
    compareTo
    0.62
    く
    0.60
    and
    0.59
     ש
    0.57
    Շ
    0.57
    鍒
    0.57
    an
    0.56
    ing
    0.56
    Activations Density 0.002%

    No Known Activations