© 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. 13767
    Prev
    Next
    INDEX
    Explanations

    intelligence gathering

    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
    (
    0.55
    -
    0.51
     ACD
    0.51
    </h2>
    0.50
    MODKEY
    0.50
    se
    0.49
     ${
    0.49
    (|
    0.49
     Darryl
    0.47
    kais
    0.47
    POSITIVE LOGITS
     hexagons
    0.59
     aphids
    0.54
     effetto
    0.52
     গুণে
    0.52
     คอม
    0.51
    рів
    0.50
    લ
    0.50
     candies
    0.49
     luxuries
    0.49
     ঘে
    0.49
    Activations Density 0.006%

    No Known Activations