© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 3965
    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
     jsem
    2.92
    ктак
    2.85
    ма
    2.78
     noqa
    2.76
    ю
    2.65
    ীয়
    2.62
    वर
    2.59
    等地
    2.58
    ⿰
    2.51
     Deserialize
    2.49
    POSITIVE LOGITS
     fuese
    3.09
     potuto
    2.92
     hiccups
    2.85
     fosse
    2.84
     ذاتی
    2.83
    ᴇ
    2.83
     এক্ষ
    2.80
     допомогти
    2.76
     аутохтони
    2.69
    Asking
    2.69
    Activations Density 0.068%

    No Known Activations