© 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. 4200
    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
    groupBox
    2.56
     mungkin
    2.56
     prosent
    2.54
    و
    2.39
     grudnia
    2.37
    Auch
    2.35
     возле
    2.33
     helt
    2.31
     específ
    2.29
    اک
    2.28
    POSITIVE LOGITS
    й
    2.95
    able
    2.70
    ة
    2.65
    }=\
    2.60
    thood
    2.47
    )<\
    2.46
    ία
    2.43
    ER
    2.42
    ת
    2.42
    handlers
    2.40
    Activations Density 0.023%

    No Known Activations