© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 33822
    Prev
    Next
    INDEX
    Explanations

    simplifying or translating text

    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_31_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
     ব্যতিক্রম
    0.33
     ಹೀ
    0.32
     rendement
    0.30
    ហេ
    0.30
    各位同學
    0.30
    Historically
    0.30
    跹
    0.30
     வகுப்பு
    0.29
     उन्हीं
    0.29
    Finale
    0.29
    POSITIVE LOGITS
     polish
    0.29
     polishing
    0.29
    input
    0.29
     파
    0.29
    xit
    0.28
     asks
    0.28
     indul
    0.28
     ফ
    0.28
     uric
    0.28
    탄
    0.28
    Activations Density 0.028%

    No Known Activations