© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 196150
    Prev
    Next
    INDEX
    Explanations

    dur

    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_50_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
     दास
    0.45
     הק
    0.43
    दास
    0.40
     крем
    0.40
     K
    0.40
     Vivo
    0.39
     энергия
    0.39
     KN
    0.38
     Pim
    0.38
    K
    0.38
    POSITIVE LOGITS
    dur
    0.52
    Poland
    0.51
     dur
    0.50
     Poland
    0.50
    Dur
    0.47
     Dur
    0.45
     Sh
    0.43
     Duro
    0.43
     Durango
    0.43
     durations
    0.42
    Activations Density 0.008%

    No Known Activations