© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 14667
    Prev
    Next
    INDEX
    Explanations

    reflexive 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_40_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
     toegang
    0.41
    Altern
    0.39
     उज्ज
    0.38
    oda
    0.38
    MARY
    0.37
    Julia
    0.37
    Viz
    0.37
    ˈ
    0.36
    Magenta
    0.35
     дорогу
    0.35
    POSITIVE LOGITS
     বিক্রি
    0.37
    標
    0.37
     metab
    0.37
     sagittal
    0.36
     меньше
    0.36
    飛び
    0.36
    ;'>
    0.35
     قلم
    0.35
     tattoo
    0.35
     perg
    0.35
    Activations Density 0.000%

    No Known Activations