© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 2932
    Prev
    Next
    INDEX
    Explanations

    time and scanner imports

    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_40_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
     brought
    0.27
    攤
    0.26
     mies
    0.26
    very
    0.25
     दशमलव
    0.25
     tricks
    0.25
    bringen
    0.25
     Son
    0.24
    grave
    0.24
     Sonora
    0.24
    POSITIVE LOGITS
     pcMove
    0.30
    QUA
    0.27
     Median
    0.26
     |--
    0.26
    䡉
    0.26
     अधिकारियों
    0.25
     מדי
    0.25
    <unused192>
    0.25
     转
    0.25
    牞
    0.25
    Activations Density 0.006%

    No Known Activations