© 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
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 30503
    Prev
    Next
    INDEX
    Explanations

    Intel CPU, Wireless, tcp dump

    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_40_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
     ressent
    0.37
     subs
    0.37
     ہار
    0.37
    Ꮡ
    0.37
     organising
    0.37
     Subs
    0.37
     motorised
    0.36
     modernisation
    0.36
    elijkheid
    0.36
     breakouts
    0.36
    POSITIVE LOGITS
    ተው
    0.41
     шабло
    0.40
     Budget
    0.39
    捎
    0.38
    ítulos
    0.38
     шаблон
    0.38
     habitudes
    0.38
     বাজেট
    0.38
     takže
    0.37
    Budget
    0.37
    Activations Density 0.071%

    No Known Activations