© 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. 111860
    Prev
    Next
    INDEX
    Explanations

    Greek letter prefixes or suffixes

    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
    st
    0.95
    kých
    0.95
    erde
    0.91
    ne
    0.87
    n
    0.86
    l
    0.85
    ر
    0.84
     collie
    0.83
    ün
    0.83
    stek
    0.80
    POSITIVE LOGITS
    0
    1.94
    ０
    1.61
    는
    1.52
     rozwiąz
    1.34
    是
    1.32
    た
    1.24
    า
    1.23
    를
    1.15
    in
    1.13
    มัน
    1.13
    Activations Density 0.000%

    No Known Activations