© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 5560
    Prev
    Next
    INDEX
    Explanations

    data preprocessing and transformation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     revelation
    0.95
     вдох
    0.92
     überras
    0.91
    answ
    0.88
    mystery
    0.87
     revelations
    0.86
    observatoire
    0.86
    磐
    0.85
     rivel
    0.83
     mystery
    0.82
    POSITIVE LOGITS
     preprocessing
    1.98
    Converting
    1.56
     preprocess
    1.55
    Preprocessing
    1.54
     Convert
    1.42
     Converting
    1.40
     حذف
    1.39
     Remove
    1.38
     transformations
    1.37
    转换为
    1.37
    Activations Density 0.720%

    No Known Activations