© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 14694
    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_13_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
    ivasena
    0.51
    fileTool
    0.50
     stylized
    0.49
    uvos
    0.49
     絵
    0.48
    jols
    0.48
    ugh
    0.47
    ilized
    0.47
     ഭ
    0.47
    zantine
    0.47
    POSITIVE LOGITS
     difficultés
    0.49
    INN
    0.47
    ن
    0.45
    TU
    0.45
    «
    0.45
    INCRE
    0.44
    CA
    0.43
     in
    0.43
    CR
    0.42
     employer
    0.42
    Activations Density 0.000%

    No Known Activations