© 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. 1694
    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
     Qxe
    2.67
    heid
    2.39
     superconduct
    2.39
     מער
    2.25
    ם
    2.23
    会自动
    2.22
    
    2.19
     bother
    2.15
     prosecutors
    2.15
    راہیم
    2.14
    POSITIVE LOGITS
    ت
    2.91
    𝐭
    2.53
    𝐝
    2.32
    س
    2.22
    ح
    2.20
    𝐢
    2.15
    𝐬
    2.13
    𝐰
    2.02
     siendo
    2.01
    ف
    2.00
    Activations Density 0.110%

    No Known Activations