© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 197978
    Prev
    Next
    INDEX
    Explanations

    math or numbers

    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_50_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
    頗
    0.40
    వి
    0.39
     pary
    0.39
     cabaret
    0.39
     kaha
    0.38
     Pablo
    0.38
     संभावित
    0.38
     zieht
    0.38
    રિક
    0.38
    で購入
    0.38
    POSITIVE LOGITS
    сія
    0.39
     테
    0.36
     tức
    0.36
    Init
    0.36
     ts
    0.35
    LIMIT
    0.34
    ເຊ
    0.34
    aphyl
    0.33
     tes
    0.33
     Contoh
    0.33
    Activations Density 0.001%

    No Known Activations