© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 80753
    Prev
    Next
    INDEX
    Explanations

    math and code constructs

    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_31_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
    dr
    0.32
    溢
    0.31
    匮
    0.30
    др
    0.30
     pédagog
    0.30
     ouvertes
    0.30
    Sandra
    0.29
     dri
    0.29
    листи
    0.29
     الدر
    0.29
    POSITIVE LOGITS
    enan
    0.33
    })^{
    0.33
     horticulture
    0.32
     दूरी
    0.31
     vorg
    0.28
    തിന്റെ
    0.28
     oynuyoruz
    0.28
    ยาน
    0.28
     ஏற்க
    0.28
     różne
    0.28
    Activations Density 0.000%

    No Known Activations