© 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. 3469
    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
    д
    3.55
    কুট
    2.76
     Primero
    2.63
    g
    2.49
    ያንዳ
    2.47
    ously
    2.47
    да
    2.46
    ನ
    2.46
    グ
    2.45
    дру
    2.45
    POSITIVE LOGITS
    u
    2.60
     IBOutlet
    2.54
    ം
    2.54
    nahme
    2.54
    les
    2.50
    𝑛
    2.48
    не
    2.47
    囁
    2.44
    𝑟
    2.43
    r
    2.39
    Activations Density 0.042%

    No Known Activations