© 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. 3842
    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
    affiliated
    2.01
     lắp
    2.00
    வ்வளவு
    1.91
     суток
    1.90
    jších
    1.82
    zony
    1.81
    bathing
    1.80
    튿
    1.76
    savvy
    1.74
     परवरिश
    1.73
    POSITIVE LOGITS
    [
    1.91
    \)
    1.87
    >
    1.82
    oretically
    1.81
     Senin
    1.74
    angleOf
    1.74
    ]
    1.68
    $
    1.68
    '$
    1.67
    {[
    1.67
    Activations Density 0.169%

    No Known Activations