© 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. 36468
    Prev
    Next
    INDEX
    Explanations

    Mumbai, Maharashtra, Marathi

    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
    ර්
    0.45
    e
    0.41
     అలా
    0.41
     Theme
    0.40
     Montserrat
    0.39
     siis
    0.38
    elsey
    0.38
     المؤس
    0.38
     tony
    0.38
     Careful
    0.38
    POSITIVE LOGITS
    zte
    0.45
     丶
    0.41
    𝐏
    0.39
     vicino
    0.38
    🕘
    0.38
     Azte
    0.38
     Paz
    0.38
    ówno
    0.37
    гато
    0.37
    quanto
    0.37
    Activations Density 0.013%

    No Known Activations