© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 252834
    Prev
    Next
    INDEX
    Explanations

    trains

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     ദൈവ
    0.37
    ﮅ
    0.37
     کړئ
    0.36
    ப்புகளை
    0.35
    笄
    0.35
    Lines
    0.35
    ggel
    0.35
    GTEST
    0.34
    ScriptInterface
    0.34
     щ
    0.33
    POSITIVE LOGITS
     train
    3.11
     Train
    2.80
     trains
    2.70
    Train
    2.69
    train
    2.64
     Trains
    2.53
    Trains
    2.52
     ट्रेन
    2.48
     rail
    2.36
    Rail
    2.14
    Activations Density 0.019%

    No Known Activations