© 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. 3741
    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
     ove
    1.55
    ,\,\,\,\
    1.39
     monedas
    1.35
    )>\
    1.32
    ,\,
    1.30
    \$
    1.29
    кра
    1.28
    BufferedReader
    1.28
    体力
    1.27
     adanya
    1.27
    POSITIVE LOGITS
    া
    1.57
    das
    1.55
    ीय
    1.48
     possess
    1.48
    ′
    1.44
     wits
    1.44
    ेशन
    1.43
    din
    1.41
    da
    1.38
    dur
    1.38
    Activations Density 0.007%

    No Known Activations