© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 9968
    Prev
    Next
    INDEX
    Explanations

    villain or evil concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_13_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
     &.
    0.54
     &
    0.51
     Verenigde
    0.50
    
    0.49
     这里
    0.48
     obchod
    0.48
     -&
    0.47
     Cote
    0.47
     Отече
    0.47
     项目
    0.47
    POSITIVE LOGITS
    ارا
    0.48
    悪
    0.47
    恶
    0.43
     personer
    0.42
     отдельных
    0.42
    Purple
    0.42
     régler
    0.42
     campa
    0.41
    map
    0.41
    لي
    0.41
    Activations Density 0.048%

    No Known Activations