© 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. 1374
    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
    न
    2.55
    al
    2.29
    ు
    2.25
    ו
    2.24
    ে
    2.12
     vrste
    2.03
    pero
    2.01
    сным
    2.01
    NSMutable
    2.00
    ように
    1.97
    POSITIVE LOGITS
    ta
    2.31
    st
    2.16
    љу
    2.08
     मिलने
    2.04
    f
    2.03
    rm
    1.95
     ardu
    1.95
    /−
    1.91
     able
    1.90
    𝖐
    1.89
    Activations Density 0.038%

    No Known Activations