© 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. 89812
    Prev
    Next
    INDEX
    Explanations

    Arsenal, Chelsea football clubs

    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
    [
    0.37
    øk
    0.31
    ار
    0.31
    '
    0.30
    ווה
    0.30
    iska
    0.29
    abilidades
    0.29
    mentar
    0.29
    ario
    0.29
    ientos
    0.29
    POSITIVE LOGITS
     Cus
    0.40
     Dio
    0.30
    茥
    0.30
     Sato
    0.30
     አገልግሎ
    0.29
    茂
    0.29
    <unused4>
    0.29
    囝
    0.29
    UserData
    0.28
     Deps
    0.28
    Activations Density 0.002%

    No Known Activations