© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 34048
    Prev
    Next
    INDEX
    Explanations

    murmurs and reactions

    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
     അപകട
    0.31
     English
    0.29
     deduced
    0.29
     Belling
    0.29
    ITO
    0.29
    olik
    0.29
    蔚
    0.29
     ইংরে
    0.28
    vento
    0.28
     Ped
    0.28
    POSITIVE LOGITS
    EXEC
    0.30
    Shutdown
    0.30
    Dance
    0.29
    Drink
    0.29
     присоеди
    0.29
    Merhaba
    0.28
     compléter
    0.28
    螯
    0.28
    SM
    0.27
    程序
    0.27
    Activations Density 0.014%

    No Known Activations