© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 202135
    Prev
    Next
    INDEX
    Explanations

    brain circuits, pathways, and regions

    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_12_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
    I
    0.57
    books
    0.55
    el
    0.54
    )):
    0.53
    Q
    0.52
    od
    0.52
    mapping
    0.52
     restaurants
    0.51
     Mapping
    0.51
    ul
    0.51
    POSITIVE LOGITS
     ENGINEERS
    0.53
    ଷ
    0.51
     FURN
    0.50
     ảnh
    0.49
    ंग
    0.48
    ည်း
    0.47
    рян
    0.47
    รร
    0.46
     trabajan
    0.46
     revolutionaries
    0.46
    Activations Density 0.004%

    No Known Activations