© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 153126
    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_23_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
     táo
    0.56
     deshalb
    0.51
     unfamiliar
    0.49
    翰
    0.49
     vẻ
    0.48
     botanical
    0.47
     Bibi
    0.47
    ifiably
    0.47
     Nuestro
    0.47
    專輯
    0.47
    POSITIVE LOGITS
    ans
    0.57
    ac
    0.56
    4
    0.52
     (“
    0.51
    ai
    0.50
    ination
    0.50
    ä
    0.50
    ۴
    0.50
    yl
    0.49
    лы
    0.49
    Activations Density 0.000%

    No Known Activations