© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 30759
    Prev
    Next
    INDEX
    Explanations

    German prepositions and adverbs

    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_7_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
    يع
    1.09
    يز
    0.98
    I
    0.92
    يف
    0.90
    الح
    0.90
    L
    0.89
    يك
    0.86
    G
    0.82
    الي
    0.82
    فيق
    0.81
    POSITIVE LOGITS
    の
    1.27
    의
    1.00
     của
    0.98
    ‌های
    0.92
    ın
    0.89
    ные
    0.85
    นะ
    0.84
     of
    0.82
    し
    0.81
    นัก
    0.78
    Activations Density 0.000%

    No Known Activations