© 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. 1756
    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
     thinker
    2.86
    तंत्र
    2.73
     tampering
    2.68
     фоне
    2.67
    น
    2.65
    ाई
    2.65
    smallskip
    2.62
    र
    2.57
    滃
    2.57
     działania
    2.55
    POSITIVE LOGITS
    <%=
    2.86
    केवल
    2.70
    ি
    2.64
    ي
    2.49
    弃
    2.42
    Hej
    2.37
    гие
    2.33
     vai
    2.30
     মতো
    2.29
    uldu
    2.28
    Activations Density 0.023%

    No Known Activations