© 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. 57588
    Prev
    Next
    INDEX
    Explanations

    in a way

    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
    on
    0.90
    ان
    0.75
    t
    0.72
    s
    0.72
    ın
    0.72
    os
    0.69
    in
    0.67
    ین
    0.64
    an
    0.64
    é
    0.62
    POSITIVE LOGITS
     postcard
    0.66
     Patagonia
    0.66
    ↵↵
    0.62
          
    0.62
     Tasmania
    0.62
     Bengal
    0.61
     ITC
    0.61
     WWII
    0.60
     polka
    0.60
    洙
    0.60
    Activations Density 0.004%

    No Known Activations