© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 42657
    Prev
    Next
    INDEX
    Explanations

    dishwashing

    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_22_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
    ｯ
    0.49
     `$
    0.48
    -$
    0.45
     اختبار
    0.45
    にっいて
    0.45
     Checker
    0.44
    ა
    0.44
     prueba
    0.44
    ($
    0.43
    ;$
    0.43
    POSITIVE LOGITS
     отказыва
    0.42
    ARIA
    0.42
    aria
    0.38
     landmarks
    0.38
    ctime
    0.37
    த்தும்
    0.37
     chambers
    0.36
    Manuel
    0.36
     traumas
    0.35
    眼的
    0.35
    Activations Density 0.001%

    No Known Activations