© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 6980
    Prev
    Next
    INDEX
    Explanations

    affectionate closings

    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_40_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
    尊
    0.43
    ropa
    0.39
     অব
    0.36
    顾
    0.36
     Olymp
    0.35
     dismiss
    0.35
     молодо
    0.35
    nament
    0.34
    гой
    0.34
    ictions
    0.34
    POSITIVE LOGITS
     kisses
    0.42
     दुख
    0.38
    substack
    0.37
    kiss
    0.37
     pancreatitis
    0.37
    ソース
    0.37
    ህ
    0.37
    Treas
    0.36
    ಲಿ
    0.36
     hawks
    0.36
    Activations Density 0.007%

    No Known Activations