© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 19383
    Prev
    Next
    INDEX
    Explanations

    keras.utils.to_categorical

    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_15_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
    व
    0.62
    H
    0.54
    海
    0.54
    P
    0.52
    海の
    0.52
    토
    0.50
    國
    0.50
     biển
    0.49
    ocean
    0.49
    ठमा
    0.49
    POSITIVE LOGITS
     Firebase
    0.61
     Vive
    0.59
     Ida
    0.57
     Ά
    0.56
     Rani
    0.56
     Ā
    0.56
     Aspergillus
    0.55
     Ανα
    0.55
     Kubernetes
    0.54
     Michelangelo
    0.54
    Activations Density 0.000%

    No Known Activations