© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 121063
    Prev
    Next
    INDEX
    Explanations

    measures, percentages, dates, and quantities

    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_27_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
     High
    0.38
     हाई
    0.34
     Swing
    0.34
     Mexico
    0.32
     Daytime
    0.32
     Necess
    0.31
     ahu
    0.31
    /
    0.31
     swing
    0.30
     म्हण
    0.30
    POSITIVE LOGITS
    옮
    0.43
    णारी
    0.38
     якая
    0.37
     proporcionar
    0.37
    тировать
    0.37
     bakteri
    0.36
     microorgan
    0.36
     userInfo
    0.36
    USTOM
    0.36
    ：（
    0.36
    Activations Density 0.001%

    No Known Activations