© 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. 2911
    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
    তে
    3.21
    y
    2.68
    ский
    2.66
    ंद
    2.46
    ories
    2.38
    ant
    2.38
    {(
    2.31
    al
    2.30
    en
    2.29
     stirring
    2.24
    POSITIVE LOGITS
    ILLIPS
    2.48
    ਰਾ
    2.39
    Commenting
    2.39
    वीं
    2.39
    الله
    2.36
     валю
    2.32
    clientX
    2.30
     stents
    2.30
     regularly
    2.29
    ت
    2.27
    Activations Density 0.002%

    No Known Activations