© 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. 217034
    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
    望
    0.39
     ло
    0.38
     ля
    0.38
     tio
    0.37
    eps
    0.36
     Lia
    0.36
     ditch
    0.36
    лети
    0.35
     om
    0.35
     sich
    0.35
    POSITIVE LOGITS
    谕
    0.41
    驄
    0.39
    maal
    0.39
    ândia
    0.39
     Tutor
    0.38
    Mole
    0.38
     MALL
    0.38
     மாதம்
    0.38
     विद्यार्थियों
    0.37
    ্কার
    0.37
    Activations Density 0.000%

    No Known Activations