© 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. 90107
    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
     Caesars
    0.58
    탉
    0.54
    3
    0.52
    の下
    0.51
    1
    0.51
    8
    0.50
    та
    0.50
     Mods
    0.48
     Struktur
    0.46
     wrestlers
    0.46
    POSITIVE LOGITS
    瑯
    0.48
    ishable
    0.45
    hesion
    0.43
    indungan
    0.43
    hanga
    0.43
     klin
    0.42
     />;
    0.42
    nale
    0.41
    dfunding
    0.41
    hom
    0.40
    Activations Density 0.000%

    No Known Activations