© 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. 2489
    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
    𝐩
    1.78
    twenty
    1.62
    IN
    1.55
    re
    1.53
    hf
    1.53
    in
    1.52
    ᴏ
    1.51
    ydı
    1.50
     innan
    1.49
    Twenty
    1.49
    POSITIVE LOGITS
    וע
    1.57
    "",
    1.49
    টি
    1.48
     thương
    1.45
    đer
    1.43
    х
    1.36
    若
    1.35
     kuti
    1.34
    я
    1.34
    ('.
    1.32
    Activations Density 0.003%

    No Known Activations