© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 101975
    Prev
    Next
    INDEX
    Explanations

    moving average

    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_14_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
    鐩
    0.52
    gard
    0.51
    ader
    0.51
    berg
    0.49
     with
    0.48
     sfor
    0.48
    Il
    0.48
    eller
    0.48
     Gaud
    0.48
     engraving
    0.47
    POSITIVE LOGITS
    ﺍ
    0.56
     లేదా
    0.54
     .)
    0.52
    وم
    0.52
     ወይም
    0.52
    вшиеся
    0.51
     judiciales
    0.51
     или
    0.50
    クロマト
    0.50
    тый
    0.50
    Activations Density 0.001%

    No Known Activations