© 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. 2356
    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
    ing
    1.81
    ης
    1.50
    ும்
    1.27
    н
    1.23
     tread
    1.19
    دی
    1.19
    ကား
    1.19
    нской
    1.16
    тів
    1.14
    ोलिक
    1.13
    POSITIVE LOGITS
    ع
    1.50
    ferences
    1.37
    气质
    1.35
    습니다
    1.34
    inture
    1.31
    良い
    1.30
    rition
    1.30
     Largest
    1.28
    tidy
    1.28
     zarówno
    1.28
    Activations Density 1.203%

    No Known Activations