© 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. 2173
    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
    ATION
    1.77
     kwargs
    1.75
    械
    1.69
    もっと
    1.67
     bụng
    1.66
    pickle
    1.62
    選択
    1.60
    なった
    1.60
     связь
    1.59
    स्ताव
    1.58
    POSITIVE LOGITS
    𝗱
    1.94
    𝘯
    1.72
    ים
    1.62
    ভাগে
    1.61
    €™
    1.57
    𝘴
    1.57
    boldsymbol
    1.54
    лих
    1.52
    ဥ
    1.50
    s
    1.47
    Activations Density 0.010%

    No Known Activations