© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 494
    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
    ಿದೆ
    2.11
    setVisible
    1.95
    什么是
    1.80
    𝙪
    1.80
    리카
    1.78
    א
    1.77
     dernières
    1.76
    𝙖
    1.74
    a
    1.72
     plead
    1.70
    POSITIVE LOGITS
    quests
    2.41
     able
    2.32
    friend
    2.26
     Bxe
    2.21
     पत्र
    1.95
     trademarks
    1.95
    ardless
    1.90
     hitters
    1.89
     raining
    1.84
     zaji
    1.82
    Activations Density 0.324%

    No Known Activations