© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 210765
    Prev
    Next
    INDEX
    Explanations

    viewport='width=device-width', initial-scale=1.0

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_20_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
     namely
    0.18
     }
    0.17
     :
    0.16
     ";
    0.15
    breviation
    0.15
    тап
    0.15
     Gomez
    0.15
    Florida
    0.15
    Fur
    0.15
    还
    0.15
    POSITIVE LOGITS
     ജില്ലാ
    0.17
     transf
    0.17
     університе
    0.16
     আত্মার
    0.16
     sélectionnés
    0.16
     Survive
    0.15
     আয়ন
    0.15
     Ünivers
    0.15
     Üniversitesi
    0.15
    膜
    0.15
    Activations Density 0.000%

    No Known Activations