© 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. 2578
    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
    𝓎
    1.37
     ग्रस्त
    1.36
     depan
    1.36
    人员
    1.34
     conceptually
    1.34
     sebenarnya
    1.33
    П
    1.29
    𝓂
    1.28
    ্যাপ
    1.27
     Zusch
    1.27
    POSITIVE LOGITS
    or
    1.70
    ка
    1.57
    ات
    1.53
    ى
    1.50
    وفر
    1.46
    viel
    1.45
     следует
    1.42
    ের
    1.41
     zel
    1.39
    س
    1.39
    Activations Density 0.057%

    No Known Activations