© 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. 12-GEMMASCOPE-2-TRANSCODER-16K
    7. 1766
    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_12_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
     usual
    0.39
    ;,
    0.38
    /,
    0.35
    ’,
    0.34
    볍
    0.34
    毘
    0.34
     abd
    0.34
     مق
    0.34
     além
    0.33
     exist
    0.33
    POSITIVE LOGITS
     extraer
    0.49
    轳
    0.41
    ্কৃত
    0.41
    indah
    0.41
     오히려
    0.40
    িকপ্ট
    0.40
     Durchmesser
    0.40
     extracción
    0.38
    Extraction
    0.38
     Brewster
    0.38
    Activations Density 0.218%

    No Known Activations