© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 135113
    Prev
    Next
    INDEX
    Explanations

    socially constructed roles and behaviors

    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_37_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
     изоли
    0.40
    }^{*}=
    0.37
     Isolated
    0.37
     সংগ্রামী
    0.37
     اخت
    0.36
    侈
    0.36
     marriages
    0.35
     وحده
    0.35
    黍
    0.35
     marrying
    0.35
    POSITIVE LOGITS
     colors
    0.63
    colors
    0.63
     Colors
    0.62
    Colors
    0.61
     colores
    0.59
     COLORS
    0.59
     रंगों
    0.56
    颜色
    0.56
     color
    0.55
    color
    0.54
    Activations Density 0.003%

    No Known Activations