© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 24717
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_10_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
     poli
    0.78
     negara
    0.73
     void
    0.71
     *
    0.70
     by
    0.68
     destru
    0.67
     side
    0.67
     long
    0.65
     representa
    0.65
     di
    0.64
    POSITIVE LOGITS
    WATER
    0.63
    тент
    0.63
    ра
    0.62
    hler
    0.61
    чку
    0.61
    Drew
    0.58
    ро
    0.57
    canoe
    0.57
    Parking
    0.57
    큘
    0.56
    Activations Density 0.000%

    No Known Activations