© 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. 45923
    Prev
    Next
    INDEX
    Explanations

    empires and minority groups

    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
    O
    0.52
     Academy
    0.48
     Accounting
    0.48
    oglio
    0.46
    C
    0.45
     Small
    0.45
    H
    0.45
     o
    0.44
     Presidente
    0.44
    c
    0.44
    POSITIVE LOGITS
     пациентов
    0.57
     пациен
    0.52
     нужна
    0.51
     соци
    0.51
     যশোর
    0.50
     exs
    0.50
     раздра
    0.49
    ୍
    0.47
    𝙏
    0.47
     رنگ
    0.47
    Activations Density 0.046%

    No Known Activations