© 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. 1564
    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
    oretically
    0.80
    s
    0.75
    不然
    0.63
    singer
    0.61
    ′,
    0.60
    י
    0.60
    sdale
    0.60
    ilibrium
    0.60
    INFRINGEMENT
    0.60
     lousy
    0.59
    POSITIVE LOGITS
    espère
    0.60
    asarray
    0.60
    КА
    0.60
     fous
    0.60
    특별시
    0.60
    À
    0.60
    лів
    0.59
    ので
    0.58
     tiene
    0.58
    let
    0.57
    Activations Density 0.136%

    No Known Activations