© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 88963
    Prev
    Next
    INDEX
    Explanations

    cultural power

    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_23_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
    業
    0.42
     ख
    0.41
    闥
    0.39
    тора
    0.38
    พบ
    0.38
     кар
    0.37
     Зем
    0.37
     bruk
    0.37
    舞
    0.37
    riks
    0.36
    POSITIVE LOGITS
    जीटी
    0.40
    价值
    0.39
     cidad
    0.39
     citoyens
    0.39
     totalPrice
    0.39
    onu
    0.38
    वीपी
    0.38
     uprisings
    0.38
    的企业
    0.38
     ઘણી
    0.38
    Activations Density 0.018%

    No Known Activations