© 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. 3770
    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
    ச
    3.16
    losti
    3.05
    ים
    2.88
     ardından
    2.73
     buah
    2.72
    (.*
    2.68
    surname
    2.60
    ה
    2.60
    ंग
    2.56
    Д
    2.55
    POSITIVE LOGITS
    ت
    3.60
    𝑔
    3.21
    ammation
    2.76
     изменений
    2.69
    า
    2.64
    naie
    2.62
     суток
    2.48
     особо
    2.47
    वादी
    2.45
     сведения
    2.44
    Activations Density 0.067%

    No Known Activations