© 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. 3242
    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
    ع
    0.89
    t
    0.86
    v
    0.77
     nominally
    0.70
    the
    0.66
    ttet
    0.63
    Scissors
    0.62
    <unused752>
    0.62
    s
    0.62
    ों
    0.62
    POSITIVE LOGITS
     reckon
    0.73
    ة
    0.70
    erne
    0.60
    ed
    0.58
    yen
    0.57
    нской
    0.56
    тья
    0.55
    ه‌ای
    0.53
    berly
    0.52
     schließlich
    0.52
    Activations Density 0.127%

    No Known Activations