© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 198822
    Prev
    Next
    INDEX
    Explanations

    JSON parsing `gson`

    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_15_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
     {{{
    0.60
    ('*
    0.59
    К
    0.58
     تقديم
    0.57
     نيك
    0.56
     партия
    0.55
    تقديم
    0.54
     تاريخ
    0.52
    ("*
    0.51
     ሌ
    0.51
    POSITIVE LOGITS
     pepp
    0.54
    anyaan
    0.52
    igure
    0.51
    rim
    0.50
    kle
    0.50
    /
    0.50
    imide
    0.49
     jelas
    0.49
    ende
    0.49
    ercise
    0.49
    Activations Density 0.000%

    No Known Activations