© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 24803
    Prev
    Next
    INDEX
    Explanations

    coding and robotics

    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
    and
    0.82
    。
    0.80
     and
    0.73
    a
    0.72
    ad
    0.69
    C
    0.68
     (
    0.66
    (
    0.66
    （
    0.66
    M
    0.65
    POSITIVE LOGITS
    ج
    0.63
    ט
    0.62
     aplicações
    0.60
     elettron
    0.58
     radiographs
    0.58
     உலோக
    0.58
    sinya
    0.57
     tienes
    0.57
     Glück
    0.57
     установка
    0.57
    Activations Density 0.000%

    No Known Activations