© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 215910
    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_50_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
    Mush
    0.40
    Tha
    0.39
    ناب
    0.39
    ebi
    0.38
    Th
    0.38
    仳
    0.38
    Purple
    0.37
     bi
    0.37
    Ind
    0.36
     DFS
    0.36
    POSITIVE LOGITS
    貥
    0.41
    闗
    0.41
    atlas
    0.38
     mik
    0.38
    ॲ
    0.38
     beh
    0.38
    okus
    0.37
     আমিন
    0.37
     Обра
    0.37
     salute
    0.37
    Activations Density 0.000%

    No Known Activations