© 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. 3837
    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
    i
    1.79
     vivo
    1.70
    ik
    1.59
    ย
    1.56
     całość
    1.54
    ک
    1.54
     gusto
    1.49
     eneste
    1.46
     fins
    1.44
    la
    1.42
    POSITIVE LOGITS
    ة
    2.21
    ित
    1.64
    केंसी
    1.61
    етки
    1.59
    원에서
    1.59
    た
    1.58
    る
    1.54
    ан
    1.54
    べく
    1.52
    lık
    1.51
    Activations Density 0.005%

    No Known Activations