© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 8922
    Prev
    Next
    INDEX
    Explanations

    change of variables and transformation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_13_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
     кли
    0.58
     {\
    0.55
     ราย
    0.53
    মে
    0.52
    ]{\
    0.52
    Mechan
    0.52
     rozwiąz
    0.51
     พา
    0.50
    izacja
    0.50
    쏠
    0.50
    POSITIVE LOGITS
     catheters
    0.55
    정에
    0.51
    鮭
    0.50
    нент
    0.50
     parmes
    0.49
    糞
    0.49
    tres
    0.48
    銑
    0.48
    計劃
    0.48
     vivent
    0.48
    Activations Density 0.027%

    No Known Activations