© 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. 3950
    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
     strides
    2.23
     вероятность
    2.08
    𝐄
    2.06
     desires
    1.96
    ந
    1.75
     els
    1.73
     اوقات
    1.72
     LoginComponent
    1.69
     Saat
    1.68
    Į
    1.68
    POSITIVE LOGITS
    ➖➖
    1.95
    в
    1.83
    فت
    1.82
    an
    1.79
    ع
    1.77
    adays
    1.77
    cellaneous
    1.74
    <0xA6>
    1.73
    ️⃣
    1.73
    )},\
    1.71
    Activations Density 0.019%

    No Known Activations