© 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. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 4163
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_2_width_16k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ارڈ
    1.30
    ҙ
    1.30
     thawed
    1.27
    десят
    1.27
    <bos>
    1.26
    ды
    1.26
    дые
    1.25
     maggiore
    1.24
    삼성
    1.24
     Cambio
    1.23
    POSITIVE LOGITS
    ்
    1.24
    此
    1.16
    andy
    1.10
     علیکم
    1.07
    $
    1.04
    ية
    1.01
     Tatsache
    1.00
    iving
    0.99
    Beans
    0.98
    at
    0.97
    Activations Density 0.002%

    No Known Activations