© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 5447
    Prev
    Next
    INDEX
    Explanations

    feelings and expressions across languages

    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_39_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
     characterised
    0.43
     visionary
    0.41
     mysticism
    0.41
     কেজি
    0.41
    迳
    0.41
     ইংরেজি
    0.40
     characterized
    0.40
    畬
    0.40
    ওয়ে
    0.39
    妣
    0.38
    POSITIVE LOGITS
    面对
    0.38
    彼此
    0.38
    自我
    0.37
     스스로
    0.37
    मंद
    0.37
     Drog
    0.36
     accompagn
    0.36
    irani
    0.35
    Alpha
    0.35
     közö
    0.35
    Activations Density 0.030%

    No Known Activations