© 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. 8957
    Prev
    Next
    INDEX
    Explanations

    dates and times

    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
    Bước
    1.46
    ină
    1.42
    ি
    1.32
    ர்
    1.22
    OL
    1.18
    luss
    1.17
    OM
    1.17
    ણી
    1.16
    י
    1.15
     อ่า
    1.13
    POSITIVE LOGITS
     ذات
    1.21
     краски
    1.20
     nearing
    1.19
    핑
    1.19
     sarees
    1.16
    $[\
    1.14
     recovering
    1.14
    ený
    1.13
     aspiring
    1.13
    ्रा
    1.12
    Activations Density 0.001%

    No Known Activations