© 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. 3292
    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
    1.95
    🙏🏻
    1.94
    ണ്ഡി
    1.87
    Haupt
    1.85
    kot
    1.84
    albeit
    1.84
    Ahora
    1.83
     années
    1.82
    ബന്ധ
    1.80
    yun
    1.80
    POSITIVE LOGITS
    お
    2.66
    ist
    2.65
    お客
    2.41
    et
    2.34
    टी
    2.29
     microglia
    2.25
     shareholder
    2.22
    ного
    2.21
     girlfriend
    2.11
     hInstance
    2.10
    Activations Density 0.433%

    No Known Activations