© 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. 1584
    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
     strane
    2.96
    م
    2.62
    鞄
    2.61
    in
    2.60
     unambiguously
    2.57
    ান
    2.52
     nei
    2.50
     intrinsically
    2.50
    میں
    2.45
    种类
    2.44
    POSITIVE LOGITS
    ท์
    2.78
    ية
    2.74
    ย์
    2.60
    ции
    2.54
    lesssim
    2.53
    ۹
    2.47
    тың
    2.45
    ᴍ
    2.44
    '){
    2.41
    𝘁
    2.41
    Activations Density 0.023%

    No Known Activations