© 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. 8971
    Prev
    Next
    INDEX
    Explanations

    World Bank data

    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
    اً
    1.17
    ্ব
    1.11
    ीय
    1.06
    از
    0.98
    اں
    0.91
    ္
    0.91
    دد
    0.90
    istä
    0.87
     ledger
    0.85
    های
    0.84
    POSITIVE LOGITS
    त्मक
    1.07
    ITECTURE
    1.03
     lineColorSpace
    0.98
    ❅
    0.95
    Dancing
    0.94
    le
    0.93
    ?,?,
    0.92
    <0xA1>
    0.91
     placental
    0.91
     streaks
    0.89
    Activations Density 0.001%

    No Known Activations