© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 53670
    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_30_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
     exception
    0.39
     terr
    0.38
    例外
    0.36
     买
    0.36
     Bern
    0.36
    corr
    0.36
     prote
    0.35
    
    0.35
     Terr
    0.34
     needed
    0.34
    POSITIVE LOGITS
    提供了
    0.38
     നേടിയ
    0.38
    ناہ
    0.37
     kaikki
    0.37
    僭
    0.37
     दूसरी
    0.36
     SVP
    0.36
    lL
    0.36
    örer
    0.35
    ayment
    0.35
    Activations Density 0.000%

    No Known Activations