© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 218770
    Prev
    Next
    INDEX
    Explanations

    investigation into legal proceedings

    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_16_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
     scanty
    0.54
     एकमात्र
    0.54
    ellers
    0.53
     высокая
    0.52
    standalone
    0.52
     親
    0.51
     complicada
    0.50
     medicina
    0.48
     leachate
    0.48
    naeus
    0.47
    POSITIVE LOGITS
     czasu
    0.51
     Nort
    0.49
     time
    0.49
    ϫ
    0.49
     Inhib
    0.48
    िति
    0.48
    ும்
    0.47
     Söz
    0.47
     year
    0.46
     dni
    0.46
    Activations Density 0.000%

    No Known Activations