© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 25649
    Prev
    Next
    INDEX
    Explanations

    declaring variables or constants

    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_10_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
     اختلاف
    0.63
     결정
    0.56
    恻
    0.54
    ю
    0.52
     対
    0.51
     忄
    0.51
    troops
    0.50
     Equilib
    0.49
    finaly
    0.49
    yiz
    0.49
    POSITIVE LOGITS
     .
    0.50
    ↵
    0.50
    ne
    0.49
     ;
    0.49
     pentru
    0.48
    .)
    0.43
     risultati
    0.43
     sano
    0.43
     and
    0.43
     fatto
    0.42
    Activations Density 0.015%

    No Known Activations