© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 61542
    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_11_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
    م
    0.58
    main
    0.50
    Main
    0.46
    Department
    0.46
    kal
    0.45
    지
    0.45
    客
    0.44
    Up
    0.43
    Des
    0.42
    Kor
    0.42
    POSITIVE LOGITS
     忄
    0.64
    рты
    0.57
     ceg
    0.56
     Tattha
    0.54
    pgamma
    0.51
     digest
    0.51
     rive
    0.50
     Elovl
    0.50
    SLICE
    0.49
     viya
    0.49
    Activations Density 0.000%

    No Known Activations