© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 8962
    Prev
    Next
    INDEX
    Explanations

    measurement units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_3_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ು
    2.22
    ر
    2.10
    ofthe
    2.04
    <0xA6>
    1.99
    WORDS
    1.98
     cline
    1.94
    aol
    1.94
    naires
    1.90
    naire
    1.87
    膀
    1.86
    POSITIVE LOGITS
     tarp
    2.11
    ுக
    2.01
    ृ
    1.99
     dernier
    1.91
    ступ
    1.89
    ա
    1.83
     immisc
    1.83
    ें
    1.83
    י
    1.79
    𝗷
    1.78
    Activations Density 0.023%

    No Known Activations