© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 215512
    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
    valuate
    0.39
    шли
    0.38
    से
    0.38
    ль
    0.38
     लोहा
    0.37
    க
    0.36
     axial
    0.36
    ^(-
    0.36
     வள்ள
    0.36
    ˳
    0.35
    POSITIVE LOGITS
    बिन
    0.42
    ᑯ
    0.42
    TOT
    0.40
     sinister
    0.40
     nez
    0.38
     Чу
    0.38
    ありがとうございます
    0.38
    Hoa
    0.38
    Marin
    0.37
    amarine
    0.37
    Activations Density 0.000%

    No Known Activations