© 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. 2238
    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
    ا
    1.21
    আজ
    1.06
     Итак
    0.97
    Вот
    0.96
     timp
    0.95
    ﺷ
    0.95
    Е
    0.95
     Nodo
    0.95
    ﺩ
    0.94
     daun
    0.92
    POSITIVE LOGITS
    theless
    1.22
    ek
    1.16
    скольку
    1.16
    क
    1.10
    ו
    1.10
    तः
    1.03
    indruck
    1.01
    chemic
    0.99
     Reasons
    0.99
    ků
    0.98
    Activations Density 0.001%

    No Known Activations