© 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. 216065
    Prev
    Next
    INDEX
    Explanations

    serial communication UART

    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
     व्हाट्स
    0.33
     authors
    0.33
     antenna
    0.32
     resection
    0.32
    彫
    0.32
     diction
    0.31
     Audio
    0.30
     antena
    0.30
     sculpt
    0.30
     dhatu
    0.30
    POSITIVE LOGITS
     वित्त
    0.33
    岐
    0.32
     পরিবেশ
    0.31
    久的
    0.31
     விட
    0.30
    财
    0.30
     രൂപ
    0.29
    boBox
    0.29
    ทะ
    0.29
    Karo
    0.29
    Activations Density 0.005%

    No Known Activations