© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 39939
    Prev
    Next
    INDEX
    Explanations

    terms

    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_57_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
     Vielen
    0.40
     lângă
    0.39
    ՝
    0.39
     კიდ
    0.37
    今天
    0.37
    
    0.37
    様に
    0.37
     وبركاته
    0.36
     বাহিরে
    0.36
    圻
    0.35
    POSITIVE LOGITS
     df
    0.42
    ôn
    0.38
    orylation
    0.38
    df
    0.37
     zahr
    0.37
    ič
    0.36
     CDF
    0.36
    ناد
    0.35
    মিস
    0.35
    صر
    0.35
    Activations Density 0.003%

    No Known Activations