© 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. 2416
    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
    \{
    3.09
    "/
    2.85
    "",
    2.66
    <0x80>
    2.64
    дьми
    2.63
    ve
    2.61
    кий
    2.47
     ℝ
    2.42
    та
    2.37
    '/
    2.36
    POSITIVE LOGITS
    ي
    2.82
     hairline
    2.72
     titt
    2.71
    ে
    2.70
    ات
    2.69
     pecinta
    2.65
     históricos
    2.62
    e
    2.60
    ेक्षित
    2.57
     paso
    2.54
    Activations Density 0.179%

    No Known Activations