© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 256292
    Prev
    Next
    INDEX
    Explanations

    python hello.py

    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_10_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
    ໂຕ
    0.84
    劧
    0.83
     가정
    0.81
     또한
    0.79
     présent
    0.78
    ettre
    0.78
    秚
    0.77
     kans
    0.77
    畨
    0.77
     rendre
    0.76
    POSITIVE LOGITS
    J
    0.80
    sg
    0.73
    ade
    0.73
    um
    0.73
    ian
    0.73
    documentation
    0.72
    y
    0.71
    yc
    0.71
    ac
    0.70
    am
    0.70
    Activations Density 0.002%

    No Known Activations