© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 1151
    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
    ம்
    2.98
    o
    2.75
    oC
    2.40
    Архівовано
    2.37
    a
    2.28
    న
    2.15
    বন্ত
    2.12
    맹
    2.12
     Kampf
    2.07
    виси
    2.04
    POSITIVE LOGITS
     cultivés
    2.72
     equivariant
    2.67
     porches
    2.64
     всего
    2.54
     plana
    2.52
    ści
    2.52
    internalType
    2.51
    ስቃሴ
    2.49
    AND
    2.47
    लेट
    2.44
    Activations Density 0.044%

    No Known Activations