© 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. 2852
    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
    д
    2.55
    सायटी
    2.12
    دی
    2.03
     actualizada
    2.01
     destinés
    1.95
    datos
    1.93
    га
    1.91
     Nacional
    1.81
     accompagne
    1.74
    но
    1.73
    POSITIVE LOGITS
     kanamycin
    2.27
    y
    1.85
    acing
    1.75
    个小时
    1.70
    רת
    1.68
    ellipse
    1.67
    పు
    1.67
    }}_
    1.66
    こと
    1.64
    yship
    1.64
    Activations Density 0.154%

    No Known Activations