© 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. 3418
    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
    ری
    2.70
    и
    2.56
    Ƒ
    2.17
    ards
    2.17
    И
    2.12
    
    2.08
    ৫
    2.08
    텐
    2.05
     уя
    2.00
    Counc
    1.98
    POSITIVE LOGITS
    zelfde
    2.61
    بدا
    2.52
    at
    2.48
    us
    2.44
    oretically
    2.41
     کننده
    2.36
    ν
    2.32
    सर्ग
    2.27
     meydana
    2.26
    oos
    2.26
    Activations Density 0.002%

    No Known Activations