© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 146500
    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_59_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
    corrh
    0.42
    CLR
    0.40
    CLASS
    0.39
    GP
    0.39
    CHS
    0.38
     E
    0.37
    res
    0.36
    ungs
    0.36
    (\
    0.36
    RES
    0.36
    POSITIVE LOGITS
     Kosten
    0.44
     तेव्हा
    0.42
     %.
    0.41
     dục
    0.40
     Pash
    0.40
     %
    0.39
     Baş
    0.39
     %)
    0.39
     erode
    0.39
     Sén
    0.39
    Activations Density 0.000%

    No Known Activations