© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 38751
    Prev
    Next
    INDEX
    Explanations

    EdTech, Edmonton, Heath

    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_3_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
    ،
    1.02
    ，
    1.02
    ।
    0.79
    、
    0.78
    v
    0.73
    ص
    0.71
     Hö
    0.70
    You
    0.68
    מ
    0.68
    بر
    0.67
    POSITIVE LOGITS
     освіти
    0.67
    ,
    0.67
    с
    0.64
    ната
    0.60
    a
    0.59
     geest
    0.57
    òa
    0.55
     drained
    0.54
    га
    0.53
    بية
    0.53
    Activations Density 0.004%

    No Known Activations