© 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. 2152
    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
     amply
    1.64
    ẋ
    1.60
     liés
    1.59
     duly
    1.59
    ➁
    1.58
    uous
    1.57
    केंसी
    1.56
    ೮
    1.55
    atched
    1.54
     раза
    1.54
    POSITIVE LOGITS
    ші
    1.88
     fruition
    1.66
    ल
    1.58
    tekn
    1.57
     তবে
    1.55
    anlı
    1.54
     consummate
    1.51
    ي
    1.51
     dàng
    1.49
    ında
    1.48
    Activations Density 0.019%

    No Known Activations