© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 642
    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
    s
    2.77
    sides
    1.92
    ع
    1.92
    აღ
    1.85
    чины
    1.83
    ता
    1.81
    selves
    1.80
    もので
    1.78
     notch
    1.77
     możliwe
    1.76
    POSITIVE LOGITS
    𝙣
    2.19
    ት
    2.15
    특별시
    2.09
    informatics
    2.09
     ৬০
    1.99
     ২৫
    1.98
    ខ្ញុំ
    1.98
     aceasta
    1.89
     شخصی
    1.89
     Pickett
    1.89
    Activations Density 0.561%

    No Known Activations