© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 127465
    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_3_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
     It
    0.69
    re
    0.62
    
    0.60
    ভাবে
    0.59
    ۰
    0.59
    </h1>
    0.58
     xây
    0.58
    féle
    0.57
    การ
    0.56
     szeret
    0.55
    POSITIVE LOGITS
    da
    0.79
    dan
    0.75
    ii
    0.73
    τη
    0.70
    a
    0.68
    تو
    0.65
    дер
    0.64
    дів
    0.64
    স্ট
    0.64
    𝘥
    0.64
    Activations Density 0.000%

    No Known Activations