© 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. 4198
    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
     been
    4.67
    been
    3.18
     gotten
    3.09
     Been
    3.06
     BEEN
    2.94
     varit
    2.81
     været
    2.69
     sido
    2.67
    Been
    2.50
    𝚞
    2.47
    POSITIVE LOGITS
    就需要
    2.94
    ع
    2.78
    र्डर
    2.70
    湧
    2.49
     صحیح
    2.45
    ée
    2.44
    빨
    2.44
    可以看到
    2.43
     juntas
    2.42
    鵑
    2.42
    Activations Density 0.002%

    No Known Activations