© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 202756
    Prev
    Next
    INDEX
    Explanations

    a long time ago

    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_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
     médica
    1.17
    ()
    0.98
    تي
    0.95
    었
    0.95
    וי
    0.93
    عين
    0.93
     veloce
    0.92
     entrop
    0.91
     aband
    0.91
    مني
    0.91
    POSITIVE LOGITS
    {
    0.99
    ۴
    0.99
    ۵
    0.90
    -}
    0.89
    csak
    0.88
    ew
    0.82
    ik
    0.81
    '
    0.81
    com
    0.80
     중요한
    0.80
    Activations Density 0.000%

    No Known Activations