© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 159997
    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_2_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
    在
    1.30
    س
    1.29
    I
    1.20
     in
    1.07
    ைட்
    1.04
     (
    1.02
    ن
    0.98
    S
    0.97
    我们
    0.96
    V
    0.96
    POSITIVE LOGITS
    is
    1.42
    ла
    1.38
    он
    1.22
    ли
    1.20
    urilor
    1.04
    ну
    1.02
    ра
    0.96
    )。
    0.96
    )।
    0.96
    ።
    0.95
    Activations Density 0.000%

    No Known Activations