© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 58364
    Prev
    Next
    INDEX
    Explanations

    country

    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_2_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
    ों
    1.08
    é
    1.07
    ات
    1.05
    าย
    1.05
     añad
    1.02
     grabando
    0.97
    ın
    0.93
     administrativos
    0.93
    ز
    0.93
    ap
    0.91
    POSITIVE LOGITS
     for
    1.84
    U
    1.45
    L
    1.35
    S
    1.30
    an
    1.23
    ни
    1.23
    V
    1.21
    né
    1.14
    в
    1.14
    in
    1.13
    Activations Density 0.003%

    No Known Activations