© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 52920
    Prev
    Next
    INDEX
    Explanations

    market research reports

    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_31_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
     padr
    0.38
    
    0.36
    មា
    0.33
     seriously
    0.32
    pcl
    0.32
    ➥
    0.30
     putra
    0.30
    iquest
    0.30
    EXPL
    0.29
    嵐
    0.29
    POSITIVE LOGITS
     Middleware
    0.34
     Object
    0.31
     objeto
    0.31
     object
    0.30
     объектов
    0.30
     Software
    0.30
     jog
    0.30
     Count
    0.29
     irland
    0.29
    ithub
    0.29
    Activations Density 0.001%

    No Known Activations