© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 40844
    Prev
    Next
    INDEX
    Explanations

    arithmetic mean and operations

    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_11_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
    定期
    0.60
    ソ
    0.59
    २०
    0.58
    מו
    0.58
    植物
    0.57
     facades
    0.56
    وي
    0.54
    jectories
    0.54
    ৫
    0.54
    が
    0.52
    POSITIVE LOGITS
    kowej
    0.58
    kowe
    0.56
     ສຳ
    0.56
    es
    0.54
     /
    0.54
     lütfen
    0.54
    :
    0.54
     arrivée
    0.54
     CLIN
    0.54
     =,
    0.54
    Activations Density 0.002%

    No Known Activations