© 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-3-4B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 3108
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_2_width_16k_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
    िक
    2.57
    й
    2.51
    ^*
    2.50
    _+
    2.47
    тер
    2.47
    allergenic
    2.47
    گار
    2.44
     freshness
    2.37
    անի
    2.35
    GFP
    2.34
    POSITIVE LOGITS
    ה
    2.85
    widetilde
    2.70
     hona
    2.62
    ați
    2.54
    स्परिक
    2.49
    eris
    2.48
    puts
    2.45
     wzgl
    2.41
    幡
    2.38
     winding
    2.37
    Activations Density 0.067%

    No Known Activations