© 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
    2. Gemma-3-4B-IT
    3. 10-GEMMASCOPE-2-TRANSCODER-262K
    4. 259642
    Prev
    Next
    INDEX
    Explanations

    restroom or bathroom related terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_10_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
     dense
    0.43
     bones
    0.40
     stimuli
    0.38
     unethical
    0.37
     photosynthetic
    0.37
     inflammatory
    0.37
    ↵
    0.37
    though
    0.36
     Cots
    0.36
     sustainable
    0.36
    POSITIVE LOGITS
    ismuth
    0.57
    版本
    0.57
    اليد
    0.54
     варі
    0.53
     tric
    0.53
     Toilet
    0.52
    <unused935>
    0.52
     sext
    0.51
    Jwt
    0.51
    ܀
    0.51
    Activations Density 0.001%

    No Known Activations