© 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. 18966
    Prev
    Next
    INDEX
    Explanations

    iris and pupils

    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
    osis
    0.54
    pop
    0.52
    folders
    0.50
    informations
    0.50
    popen
    0.50
    $('.
    0.48
     Meyer
    0.48
    copper
    0.48
    Hybrid
    0.48
    [
    0.48
    POSITIVE LOGITS
     bowled
    0.56
    深夜
    0.53
    전히
    0.50
     aan
    0.49
     TESTS
    0.48
     величе
    0.47
    ೂರ್ಣ
    0.47
    に着
    0.47
     жаңы
    0.47
    ја
    0.46
    Activations Density 0.002%

    No Known Activations