© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 67755
    Prev
    Next
    INDEX
    Explanations

    bathing

    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_46_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
     pool
    2.02
     Pool
    1.95
    Pool
    1.90
    pool
    1.75
    池
    1.54
    POOL
    1.50
     pools
    1.41
     池
    1.30
     Pools
    1.28
     पूल
    1.25
    POSITIVE LOGITS
     bathing
    1.35
     bathe
    1.19
     купа
    1.09
     Bath
    1.07
     bath
    1.05
    bathing
    1.04
     bathed
    0.97
    Bath
    0.96
     tắm
    0.94
    浴
    0.93
    Activations Density 0.005%

    No Known Activations