© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 213951
    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_16_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
     desenvolv
    0.56
    ية
    0.52
    ток
    0.51
     તમારે
    0.50
     preserv
    0.49
     desarrollan
    0.49
     vicenda
    0.49
    හ
    0.48
    ड्यूल
    0.48
     reú
    0.48
    POSITIVE LOGITS
    teman
    0.51
    ering
    0.47
    diction
    0.45
    ings
    0.45
     Region
    0.44
    gus
    0.43
     параметр
    0.43
    ää
    0.42
     region
    0.42
     direction
    0.42
    Activations Density 0.000%

    No Known Activations