© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 124840
    Prev
    Next
    INDEX
    Explanations

    I language pronouns

    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_37_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
    先生
    0.39
     lexical
    0.37
     ingenious
    0.36
     حضرتك
    0.34
    圯
    0.33
    вут
    0.33
     선생님
    0.32
     xổ
    0.32
     admiss
    0.32
     Uns
    0.32
    POSITIVE LOGITS
     tôi
    1.30
     আমি
    1.29
    我
    1.29
     मैंने
    1.27
     मैं
    1.23
     நான்
    1.20
     ನಾನು
    1.19
     నేను
    1.18
     saya
    1.17
    ผม
    1.15
    Activations Density 0.265%

    No Known Activations