© 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. 45907
    Prev
    Next
    INDEX
    Explanations

    wash hand basin, washing hands thoroughly

    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
     RequestMethod
    0.29
    بحث
    0.27
     Kapp
    0.27
    ぜひ
    0.26
    abilitas
    0.26
     NodeType
    0.25
    㭐
    0.25
    )】
    0.25
    Particle
    0.25
    bumptech
    0.25
    POSITIVE LOGITS
     rere
    0.32
     arriving
    0.31
     migrated
    0.28
     sais
    0.26
     peeps
    0.26
     catalogues
    0.26
     checkbox
    0.26
     threaded
    0.26
    date
    0.25
     regroup
    0.25
    Activations Density 0.000%

    No Known Activations