© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 46-GEMMASCOPE-2-TRANSCODER-262K
    4. 198385
    Prev
    Next
    INDEX
    Explanations

    specific entities

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     გამოი
    0.41
     commemorating
    0.40
    মার্ক
    0.39
     семи
    0.38
     inci
    0.38
    unków
    0.37
     ሶ
    0.37
     дости
    0.37
     reconnu
    0.37
     Yous
    0.37
    POSITIVE LOGITS
     culto
    0.42
     اللّه
    0.41
     الله
    0.40
    ฐ
    0.39
     पड़
    0.38
    菁
    0.37
     Tender
    0.37
    pis
    0.36
     Wag
    0.36
    Square
    0.36
    Activations Density 0.010%

    No Known Activations