© 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. 1765
    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
     fact
    3.15
    ㅈ
    2.77
    sce
    2.68
    ளமான
    2.66
     बढ़ाने
    2.64
    sync
    2.63
    some
    2.62
    ों
    2.60
    язы
    2.59
    ের
    2.58
    POSITIVE LOGITS
    𝓈
    3.08
     वेळी
    2.79
    به
    2.65
     Пусть
    2.61
     Chaque
    2.59
     sledge
    2.59
     tranche
    2.49
     വേ
    2.45
     helplessly
    2.45
     spaced
    2.42
    Activations Density 0.007%

    No Known Activations