© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 9068
    Prev
    Next
    INDEX
    Explanations

    multi-language list separators

    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_40_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
     أيضًا
    0.51
     给
    0.48
     ਵੀ
    0.46
     بھی
    0.46
    ıyor
    0.46
    휋
    0.45
    篦
    0.45
     mengingat
    0.44
     مِنْ
    0.44
     ОТ
    0.44
    POSITIVE LOGITS
    กระ
    0.81
    ค
    0.80
    ปัญหา
    0.79
    ที่
    0.79
    ส
    0.79
    ความ
    0.78
    อย่าง
    0.78
    ข้อ
    0.78
    การ
    0.77
    แ
    0.76
    Activations Density 0.054%

    No Known Activations