© 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. 3086
    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
    可以
    3.15
    可以选择
    2.84
    و
    2.67
    僅
    2.54
    ج
    2.53
    ल्पनिक
    2.44
     ity
    2.39
    ے
    2.37
     pointA
    2.37
    <unused688>
    2.36
    POSITIVE LOGITS
    ва
    3.13
    𝗶
    2.71
    ен
    2.64
    𝗮
    2.64
    ам
    2.63
    𝖔
    2.58
    𝗲
    2.50
    
    2.43
    vening
    2.33
    ി
    2.33
    Activations Density 0.029%

    No Known Activations