© 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. 2663
    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
    та
    3.66
     fend
    2.95
    ine
    2.80
    서를
    2.69
    ៉
    2.68
    ders
    2.62
    тата
    2.61
    Ι
    2.54
    distant
    2.52
    फ
    2.51
    POSITIVE LOGITS
     materiál
    2.60
    a
    2.58
    ા
    2.56
    立つ
    2.50
    ка
    2.48
    ANCE
    2.41
     собой
    2.41
    <bos>
    2.40
    hite
    2.36
    ธ์
    2.36
    Activations Density 0.025%

    No Known Activations