© 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. 9221
    Prev
    Next
    INDEX
    Explanations

    increasingly

    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
    ড
    2.48
    ں
    2.45
     ute
    2.37
    ना
    2.05
    goed
    2.05
    ार
    2.00
    𝗷
    1.97
     фильмов
    1.96
    𝘇
    1.95
    勻
    1.92
    POSITIVE LOGITS
     सहमति
    2.02
    라인
    2.01
     accustomed
    1.95
     třeba
    1.92
    想起
    1.91
    ง
    1.91
    raisal
    1.86
    м
    1.86
    kę
    1.85
    iają
    1.84
    Activations Density 0.085%

    No Known Activations