© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 179336
    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_24_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
     unang
    0.45
     മു
    0.43
     Western
    0.43
    ë
    0.43
     initio
    0.43
    ast
    0.42
    Assignment
    0.42
     engag
    0.42
    ัด
    0.42
     Commission
    0.41
    POSITIVE LOGITS
     restauración
    0.50
    icolor
    0.50
    店舗
    0.49
    ブログ
    0.48
    suitable
    0.48
     aclar
    0.48
     funcionarios
    0.48
     აღმასრულ
    0.47
    𝑤
    0.47
     bikes
    0.47
    Activations Density 0.000%

    No Known Activations