© 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. 2994
    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
    т
    2.83
    ﺩ
    2.40
    د
    2.20
    一带
    2.14
    era
    2.12
     dati
    2.06
    лдуу
    2.06
     pomeriggio
    2.04
    ्तिक
    2.01
    дный
    2.00
    POSITIVE LOGITS
    которые
    2.40
    смотря
    2.37
    લા
    2.22
     FormsModule
    2.19
    )}},
    2.08
    لاً
    2.02
    
    2.01
    falls
    2.00
    ু
    1.98
     morphisms
    1.98
    Activations Density 0.001%

    No Known Activations