© 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. 2932
    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
    ية
    2.16
    omorphism
    1.80
    DEFGHIJKLMNOP
    1.80
    -}$
    1.72
    ment
    1.72
    DropDownStyle
    1.64
    cing
    1.62
    ystem
    1.59
    ır
    1.58
     Xinhua
    1.57
    POSITIVE LOGITS
    ста
    1.74
    ઓમાં
    1.65
    ش
    1.64
    شو
    1.61
    Основные
    1.59
    ઓની
    1.59
     accede
    1.58
     lauf
    1.57
    ঠাকুর
    1.52
    দর
    1.49
    Activations Density 0.019%

    No Known Activations