© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 35420
    Prev
    Next
    INDEX
    Explanations

    fiber, seeds, full, satiety

    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_11_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
     गड़ब
    0.54
     undermining
    0.52
     transmissions
    0.52
    ஊ
    0.52
     bilgiler
    0.50
     chimeric
    0.50
     erred
    0.50
    കർ
    0.49
     undermined
    0.48
     serializers
    0.48
    POSITIVE LOGITS
    P
    0.59
    ol
    0.58
    W
    0.56
    edra
    0.54
    AN
    0.53
    edal
    0.51
     Game
    0.51
    ed
    0.50
    G
    0.50
    an
    0.50
    Activations Density 0.034%

    No Known Activations