© 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. 2479
    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
    й
    3.02
    ことになる
    2.99
    е
    2.81
    м
    2.70
    erweise
    2.67
     cht
    2.61
    ően
    2.61
    ʟ
    2.59
    бин
    2.47
    𝑒
    2.43
    POSITIVE LOGITS
     pliers
    2.82
    ون
    2.78
    యు
    2.68
    ০০
    2.61
    ۰۰
    2.58
    ूंकि
    2.58
    ан
    2.54
     Parses
    2.50
    eer
    2.47
    ます
    2.39
    Activations Density 0.011%

    No Known Activations