© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 227151
    Prev
    Next
    INDEX
    Explanations

    Dutch pronoun 'je'

    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_6_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
    لي
    1.30
     غير
    1.28
    يان
    1.27
     وي
    1.21
    رير
    1.20
     تحقيق
    1.17
    ير
    1.16
    ي
    1.16
     يت
    1.13
    د
    1.13
    POSITIVE LOGITS
    s
    1.80
    ;
    1.37
    ی
    1.37
    I
    1.33
    ের
    1.17
    2
    1.17
     critic
    1.14
    ↵
    1.13
    ल
    1.13
    ς
    1.13
    Activations Density 0.000%

    No Known Activations