© 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. 404
    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
    י
    1.64
    ي
    1.49
    м
    1.38
    an
    1.37
    н
    1.32
    ان
    1.32
    ту
    1.30
    д
    1.27
    stackrel
    1.19
     dotyczą
    1.18
    POSITIVE LOGITS
     čega
    1.13
     особенностей
    1.07
     интере
    0.99
     middel
    0.97
    েনারেল
    0.97
     dotted
    0.95
    𝑠
    0.94
     coerc
    0.94
     niego
    0.92
    ѕ
    0.92
    Activations Density 0.985%

    No Known Activations