© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 18529
    Prev
    Next
    INDEX
    Explanations

    project or product

    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_34_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
    Maker
    0.37
     proizvođa
    0.37
    lisher
    0.37
    vercel
    0.36
    ヅ
    0.36
     الاخ
    0.35
     버
    0.35
    涨
    0.35
     Versace
    0.35
     Grower
    0.35
    POSITIVE LOGITS
     проекта
    0.50
     продукт
    0.49
     продукта
    0.49
     universality
    0.48
     project
    0.47
     проект
    0.47
     proiect
    0.47
     প্রকল্পটি
    0.46
     proyecto
    0.45
     проекту
    0.43
    Activations Density 0.124%

    No Known Activations