© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 109142
    Prev
    Next
    INDEX
    Explanations

    i followed by various characters

    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_2_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
    ين
    2.00
    ות
    1.42
    ير
    1.41
    تي
    1.35
    리
    1.29
    in
    1.23
    ли
    1.20
    لي
    1.15
    ৬
    1.13
    ي
    1.11
    POSITIVE LOGITS
    1.10
    of
    0.97
    дят
    0.97
    ために
    0.93
     investasi
    0.91
    ۵
    0.91
    हा
    0.90
    า
    0.90
     analisis
    0.89
     زمانی
    0.89
    Activations Density 0.001%

    No Known Activations