© 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. 195245
    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
     provoking
    0.44
     ускори
    0.40
     fades
    0.40
    arco
    0.40
     cristal
    0.39
    кри
    0.39
    嗪
    0.38
    ফুজ
    0.37
    绡
    0.37
    粥
    0.36
    POSITIVE LOGITS
    ಂಧ
    0.41
    Sew
    0.40
     CONTENTS
    0.40
     ανα
    0.39
    ripe
    0.39
    Technology
    0.38
    Miranda
    0.38
    Bam
    0.38
    Latch
    0.38
     ಆ
    0.37
    Activations Density 0.000%

    No Known Activations