© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 30632
    Prev
    Next
    INDEX
    Explanations

    cleanliness and comfort

    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_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
     Salam
    0.38
    ⎟
    0.36
     électron
    0.35
     Balt
    0.34
     pavements
    0.33
     Bonus
    0.33
     chats
    0.32
     workouts
    0.32
     Walnut
    0.32
     Softball
    0.32
    POSITIVE LOGITS
    清潔
    0.45
    Cleaning
    0.41
    清洁
    0.39
    ć
    0.37
     cleanliness
    0.37
     uncl
    0.37
     cleaning
    0.36
     پاک
    0.36
     ناول
    0.35
    清理
    0.35
    Activations Density 0.003%

    No Known Activations