© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 203453
    Prev
    Next
    INDEX
    Explanations

    urinal, Vatican, urine, bacteria

    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_12_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
    🚽
    0.57
     toilets
    0.54
     restrooms
    0.53
    トイレ
    0.51
    читься
    0.49
     apparaissent
    0.49
     apporter
    0.48
    തായ
    0.48
    তরাং
    0.48
    תן
    0.47
    POSITIVE LOGITS
     life
    0.54
    religious
    0.52
    One
    0.51
    iczne
    0.48
    has
    0.47
    <b>
    0.46
    Di
    0.46
    He
    0.45
    \
    0.45
    sand
    0.44
    Activations Density 0.022%

    No Known Activations