© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 24058
    Prev
    Next
    INDEX
    Explanations

    bath

    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_56_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
     bath
    1.38
    Bath
    1.26
     Bath
    1.24
    bath
    1.17
     BATH
    1.13
     baths
    1.06
     bathing
    0.95
    浴
    0.95
     bathroom
    0.94
    bathroom
    0.92
    POSITIVE LOGITS
    making
    0.39
    நீர்
    0.37
    stdout
    0.36
     تای
    0.36
    resist
    0.36
    res
    0.36
    water
    0.36
    水
    0.35
    釘
    0.35
     বল
    0.35
    Activations Density 0.001%

    No Known Activations