© 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. 102304
    Prev
    Next
    INDEX
    Explanations

    `Key? key` constructor parameter

    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_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
     neumáticos
    0.47
     duplic
    0.47
     zaten
    0.46
     modifica
    0.46
    測試
    0.45
    鏉
    0.45
     speculation
    0.44
     Already
    0.44
     conformation
    0.44
     transmiss
    0.44
    POSITIVE LOGITS
    ie
    0.54
    íč
    0.54
    kä
    0.52
    ổ
    0.52
    k
    0.52
    ills
    0.51
    ilibr
    0.49
    etse
    0.48
    í
    0.48
    kých
    0.46
    Activations Density 0.000%

    No Known Activations