© 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. 199275
    Prev
    Next
    INDEX
    Explanations

    yoga flow ashtanga vinyasa

    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
     rea
    0.55
     headlights
    0.54
     IAAF
    0.53
     বিশ্বকাপ
    0.52
     Finanz
    0.52
     Fulham
    0.52
     خانہ
    0.52
    ᇁ
    0.52
    𝘂
    0.51
     Urea
    0.51
    POSITIVE LOGITS
     imagery
    0.53
     commerce
    0.50
    лизм
    0.50
    льм
    0.49
    gimento
    0.48
     motion
    0.47
    بی
    0.46
    bordered
    0.46
     storytelling
    0.46
     awoke
    0.45
    Activations Density 0.001%

    No Known Activations