© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 37224
    Prev
    Next
    INDEX
    Explanations

    physics and physical research

    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
    EN
    0.59
     最大
    0.58
    學生
    0.56
    ുകളെ
    0.55
    漀
    0.54
     pháp
    0.53
    幫助
    0.51
    ENU
    0.51
     encourage
    0.50
     દ્વારા
    0.49
    POSITIVE LOGITS
    t
    0.64
     Sacrament
    0.57
     campes
    0.52
     Mesopot
    0.52
     enfermo
    0.51
    이브
    0.51
    Leftrightarrow
    0.50
    uins
    0.50
     থাকেন
    0.49
    villa
    0.49
    Activations Density 0.005%

    No Known Activations