© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 206202
    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_46_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
    сово
    0.39
     CB
    0.39
     GLFW
    0.39
     redshifts
    0.38
     commute
    0.38
     goods
    0.38
    暹
    0.38
     بسی
    0.37
     Vall
    0.37
    ampur
    0.37
    POSITIVE LOGITS
     Copyright
    0.52
    Copyright
    0.46
     copyright
    0.42
     Licensed
    0.42
    ುದು
    0.40
    ('../
    0.38
    ="../
    0.37
    ceva
    0.36
    Licensed
    0.36
     copyrighted
    0.35
    Activations Density 0.000%

    No Known Activations