© 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. 32310
    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
    伯
    0.45
    Berk
    0.39
    Ѕ
    0.38
     পর্দা
    0.38
    Bir
    0.37
     بیر
    0.37
     Bir
    0.37
    ና
    0.36
     गै
    0.36
    બર
    0.35
    POSITIVE LOGITS
     Az
    0.78
    azam
    0.67
    Az
    0.64
     az
    0.63
     आजम
    0.61
     اعظم
    0.61
    azim
    0.54
     azimuth
    0.53
    ظم
    0.52
     AZ
    0.52
    Activations Density 0.000%

    No Known Activations