© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 231621
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_6_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
    t
    1.05
    ت
    0.87
    n
    0.67
    ر
    0.63
    .
    0.61
     in
    0.57
    ن
    0.57
    ↵
    0.56
    ла
    0.56
     lipids
    0.55
    POSITIVE LOGITS
     វា
    0.55
     উদ্যোগে
    0.54
    onimo
    0.54
     從
    0.53
     तौर
    0.52
     nó
    0.51
    ceso
    0.50
    ovač
    0.50
    ảo
    0.49
     două
    0.49
    Activations Density 0.000%

    No Known Activations