© 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. 3123
    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
    3.06
    ли
    3.05
    त
    2.98
    л
    2.85
    ן
    2.79
    ु
    2.77
    या
    2.70
     Litigation
    2.70
     commutative
    2.63
    dancer
    2.63
    POSITIVE LOGITS
    antia
    2.70
    que
    2.37
    rzeć
    2.35
    uenti
    2.34
    s
    2.33
    ক
    2.27
    আ
    2.26
     ndani
    2.19
    ровкой
    2.18
    szer
    2.18
    Activations Density 0.179%

    No Known Activations