© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 211191
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_20_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     couvrir
    0.50
     mạch
    0.48
     payer
    0.46
     renforcer
    0.46
     gérer
    0.45
    ده
    0.45
    ιχ
    0.44
     &_
    0.44
    솝
    0.43
     দেখিতে
    0.43
    POSITIVE LOGITS
     disruptive
    0.44
     unacceptable
    0.44
    )».
    0.43
    Когда
    0.42
     ).
    0.41
    ()).
    0.41
     embarrassing
    0.41
     ink
    0.41
    երը
    0.40
    Очень
    0.39
    Activations Density 0.000%

    No Known Activations