© 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. 26620
    Prev
    Next
    INDEX
    Explanations

    ITER, Tokamak, price

    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
    0.55
    THE
    0.52
    illac
    0.51
    л
    0.50
    (),
    0.49
    andeep
    0.49
     Duff
    0.49
    Ì
    0.48
     and
    0.48
     specjal
    0.47
    POSITIVE LOGITS
     Exports
    0.54
    بلا
    0.51
     सला
    0.51
    ંપની
    0.51
     examines
    0.50
    地区的
    0.50
     экрана
    0.50
    ྰ
    0.49
     was
    0.48
     asks
    0.48
    Activations Density 0.000%

    No Known Activations