© 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. 2106
    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
    了
    2.60
     числе
    2.57
     communion
    2.49
     получение
    2.43
     incluem
    2.34
    ма
    2.33
     нет
    2.29
     rửa
    2.27
    Correlation
    2.27
     проведение
    2.25
    POSITIVE LOGITS
    ून
    2.72
    fully
    2.25
    ിച്ച്
    2.14
    魎
    2.12
    ্নার
    2.10
     '\\;'
    2.05
    checkFor
    2.04
     sparingly
    2.03
     reprend
    2.02
    zame
    1.99
    Activations Density 0.259%

    No Known Activations