© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 215882
    Prev
    Next
    INDEX
    Explanations

    why would

    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_31_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
    この
    0.46
    平板
    0.39
     stiff
    0.39
    Wherever
    0.38
     této
    0.38
    ಟೆ
    0.37
    ᠢ
    0.36
    This
    0.35
    す
    0.35
    igli
    0.34
    POSITIVE LOGITS
     anciens
    0.46
     ограни
    0.43
     siden
    0.39
     decrement
    0.38
     enzymes
    0.38
    ⤥
    0.37
     limitaciones
    0.37
     Deja
    0.36
    링
    0.36
     Cedex
    0.36
    Activations Density 0.001%

    No Known Activations