© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 1448
    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
     narrator
    1.16
     amused
    1.13
     else
    1.04
    ك
    1.04
    <bos>
    1.04
    ও
    1.03
    উল্লেখ্য
    1.03
     scaff
    1.02
    邬
    1.02
     extensively
    1.01
    POSITIVE LOGITS
    ти
    1.57
     perceber
    1.14
     seves
    1.13
     mises
    1.09
    ра
    1.05
     fleste
    1.05
     seguintes
    1.03
     dollars
    1.03
    生
    1.03
    ট
    1.02
    Activations Density 0.039%

    No Known Activations