© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 110545
    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_2_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
    et
    0.94
    at
    0.84
    ين
    0.84
    يد
    0.79
    т
    0.75
    ak
    0.73
    은
    0.70
    AN
    0.69
    ية
    0.65
    ้
    0.65
    POSITIVE LOGITS
     entrees
    0.71
     incompat
    0.67
     decreases
    0.64
    la
    0.64
     perturbations
    0.64
     (
    0.64
     concili
    0.62
     eyelashes
    0.62
     for
    0.60
     suscept
    0.59
    Activations Density 0.000%

    No Known Activations