© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 1456
    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
    ﻫ
    1.57
    檎
    1.46
    hood
    1.39
     είναι
    1.38
    coon
    1.37
     Jadeja
    1.34
     nucleon
    1.31
    Similarity
    1.30
     ने
    1.29
     ঢুকে
    1.27
    POSITIVE LOGITS
    el
    1.69
    க
    1.54
    संद
    1.38
    От
    1.36
     darn
    1.34
    ма
    1.33
    не
    1.29
     Falle
    1.28
    or
    1.28
     worst
    1.26
    Activations Density 0.023%

    No Known Activations