© 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. 2203
    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
     zejména
    2.18
    dien
    2.12
     součástí
    2.10
    Ο
    2.06
     davran
    2.06
    नि
    2.03
     bawah
    2.03
     выбирать
    2.03
     św
    2.02
    
    2.01
    POSITIVE LOGITS
     Кто
    2.25
    в
    2.14
     annihil
    2.13
     UserManager
    2.09
    娲
    2.03
     thalassemia
    2.02
     groupId
    2.01
    檚
    1.98
    ity
    1.94
    Стро
    1.91
    Activations Density 0.009%

    No Known Activations