© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 155380
    Prev
    Next
    INDEX
    Explanations

    negation

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     T
    0.71
     t
    0.62
     الت
    0.60
    T
    0.55
    انية
    0.54
     ت
    0.51
    Ｔ
    0.50
    اني
    0.49
     ta
    0.48
     т
    0.47
    POSITIVE LOGITS
     بتكون
    0.54
     بيكون
    0.48
     بتر
    0.39
    obie
    0.38
    sej
    0.37
    ลัง
    0.37
     পাচ্ছি
    0.36
     بتق
    0.36
     দেখছি
    0.36
    めている
    0.35
    Activations Density 0.001%

    No Known Activations