© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 130329
    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_6_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
    li
    1.23
    os
    1.16
    t
    1.09
    al
    1.05
    deki
    1.04
    ก
    1.03
    5
    1.02
    re
    1.02
    g
    1.02
    3
    1.02
    POSITIVE LOGITS
    ,
    0.98
    р
    0.92
     بیاکت
    0.86
     so
    0.84
     supplies
    0.83
     says
    0.82
     splits
    0.79
     diagnoses
    0.78
     sprays
    0.77
     распростран
    0.77
    Activations Density 0.000%

    No Known Activations