© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 30140
    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_7_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
     Bibliothèque
    0.54
    ႉ
    0.54
     descends
    0.52
     ફિલ્
    0.51
     tricked
    0.50
     Jalis
    0.49
     Coolidge
    0.49
     poissons
    0.48
     Lobkowicz
    0.48
     dynasty
    0.48
    POSITIVE LOGITS
    ف
    0.62
    ए
    0.51
    DIM
    0.49
    چ
    0.49
    为了
    0.48
    شوند
    0.47
    M
    0.47
    最
    0.47
    大幅
    0.47
    i
    0.47
    Activations Density 0.000%

    No Known Activations