© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 35658
    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_11_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
     Brescia
    0.46
     têm
    0.43
    fluent
    0.42
    値下げ
    0.42
     diferenci
    0.41
     angl
    0.41
    纬
    0.41
     proven
    0.41
    ഴ്ച
    0.41
     Tsuen
    0.41
    POSITIVE LOGITS
    ل
    0.57
     or
    0.50
    لا
    0.50
    то
    0.49
    to
    0.49
     Enter
    0.48
    ць
    0.48
     Ending
    0.48
     to
    0.48
    Enter
    0.46
    Activations Density 0.000%

    No Known Activations