© 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. 1011
    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
    ם
    1.57
     methionine
    1.54
    δου
    1.51
     thừa
    1.50
    আমি
    1.46
     boleh
    1.43
     же
    1.42
    possibly
    1.40
     shouted
    1.40
     toBe
    1.37
    POSITIVE LOGITS
    u
    1.70
     davantage
    1.54
    o
    1.40
    localVarHTTP
    1.37
    हद
    1.37
    ϲ
    1.36
    े
    1.35
     Bxe
    1.35
     pamoja
    1.34
    隍
    1.33
    Activations Density 0.042%

    No Known Activations