© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 28689
    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_10_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
     chaotic
    0.49
     relic
    0.49
    ాను
    0.48
    로
    0.48
    ኃ
    0.48
    뻔
    0.47
     meiosis
    0.46
    れ
    0.46
    뻗
    0.46
    
    0.46
    POSITIVE LOGITS
    OP
    0.54
     dansk
    0.47
     i
    0.47
    aby
    0.46
     routing
    0.45
    of
    0.44
    bst
    0.44
    adeh
    0.43
    who
    0.43
     وو
    0.43
    Activations Density 0.000%

    No Known Activations