© 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. 195020
    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
     Ka
    0.42
    モリ
    0.41
     अंका
    0.39
     capitalise
    0.39
     ka
    0.38
     hama
    0.37
     ബ
    0.37
    Compounds
    0.37
    カ
    0.36
    बिलिटी
    0.36
    POSITIVE LOGITS
    otrophic
    0.43
    윽
    0.42
     Marguerite
    0.40
     Ấ
    0.39
    éph
    0.39
     ஏற்று
    0.38
    otron
    0.38
     अरुण
    0.38
     ያለው
    0.38
     முன்
    0.37
    Activations Density 0.000%

    No Known Activations