© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 233074
    Prev
    Next
    INDEX
    Explanations

    wedding planner or between

    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_32_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
     ثانيه
    0.40
     lime
    0.38
     suger
    0.38
     minima
    0.37
     factorization
    0.37
    inserts
    0.37
    聾
    0.37
     মহাশয়
    0.37
     subtype
    0.36
    traditional
    0.35
    POSITIVE LOGITS
    plac
    0.40
    ব্ল
    0.40
    举
    0.39
    resposta
    0.37
    क्यू
    0.36
    launcher
    0.35
    计数
    0.35
     回転
    0.35
     WHIT
    0.34
     Wh
    0.33
    Activations Density 0.001%

    No Known Activations