© 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. 49537
    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_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
     Journalist
    0.41
    dataFile
    0.39
     "_"
    0.36
    journalist
    0.36
     segmental
    0.36
     datafile
    0.36
     centered
    0.36
     সাবেক
    0.35
     ಮಾಹಿತಿ
    0.35
     intensive
    0.35
    POSITIVE LOGITS
    映像
    0.39
     kpc
    0.39
     गै
    0.36
     produktów
    0.34
    축
    0.34
    ြ
    0.33
    Intro
    0.33
    產品
    0.33
     jinak
    0.33
    ंटे
    0.32
    Activations Density 0.000%

    No Known Activations