© 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. 2545
    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
    ður
    2.76
    ва
    2.71
    ➙
    2.69
    ем
    2.57
    НІ
    2.48
    r
    2.43
    με
    2.43
    nement
    2.42
     actomyosin
    2.42
     prête
    2.38
    POSITIVE LOGITS
    й
    3.27
    ع
    2.81
    ので
    2.74
     facendo
    2.65
    ্টা
    2.42
    라도
    2.37
    bik
    2.35
    fica
    2.34
    dados
    2.33
     MediaQuery
    2.32
    Activations Density 0.054%

    No Known Activations