© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 77224
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    週期
    0.41
     psycho
    0.39
     quickly
    0.37
     좋
    0.37
    isdigit
    0.37
     sugest
    0.37
    中最
    0.37
     linking
    0.36
     जल्दी
    0.36
    
    0.35
    POSITIVE LOGITS
     Ори
    0.39
     квартиры
    0.38
    เซอร์
    0.37
     пласти
    0.37
    вір
    0.36
     cort
    0.35
    叠加
    0.35
    ንግ
    0.35
     Лон
    0.34
     корре
    0.34
    Activations Density 0.000%

    No Known Activations