© 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. 79417
    Prev
    Next
    INDEX
    Explanations

    1 =

    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
    
    0.33
    ्यूशन
    0.31
    mocks
    0.31
    ͙
    0.30
    游戏
    0.29
    Analyser
    0.29
    苙
    0.29
    amenti
    0.29
     Australien
    0.29
     perfume
    0.29
    POSITIVE LOGITS
    เรีย
    0.30
     neo
    0.29
    стов
    0.29
     oat
    0.29
    請
    0.29
    ொழுது
    0.28
    isst
    0.28
     southwest
    0.28
     none
    0.28
     сво
    0.28
    Activations Density 0.002%

    No Known Activations