© 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. 8967
    Prev
    Next
    INDEX
    Explanations

    chowder

    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
    ️⃣
    3.04
    𝜇
    2.93
    ively
    2.86
    ر
    2.80
     вариантов
    2.79
    fully
    2.73
    в
    2.59
    ⃣
    2.49
    ère
    2.48
     draftsman
    2.43
    POSITIVE LOGITS
    もら
    3.37
     Mesmo
    2.38
     doulou
    2.35
    ም
    2.30
     сни
    2.28
    贯彻
    2.22
    ও
    2.20
    ᱚ
    2.18
    उट
    2.14
     constitucional
    2.12
    Activations Density 0.000%

    No Known Activations