© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 49104
    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
     ज्‍यादा
    0.53
    ⁣
    0.51
    选
    0.48
    事人
    0.47
    antad
    0.47
     Colombeau
    0.47
    ೀಯ
    0.47
    "+"|".
    0.45
     гар
    0.44
     monarchs
    0.44
    POSITIVE LOGITS
     mound
    0.50
     데이터
    0.50
     df
    0.49
    JS
    0.49
    df
    0.48
     database
    0.46
     võimal
    0.46
     bila
    0.45
     ਕੀ
    0.45
     бекер
    0.45
    Activations Density 0.000%

    No Known Activations