© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 34904
    Prev
    Next
    INDEX
    Explanations

    language translation and code conversion

    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_11_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     মন্ত্রী
    0.44
    ER
    0.42
    𝒌
    0.40
    潴
    0.39
    requests
    0.39
    kk
    0.38
    که
    0.38
    ता
    0.37
     عمومی
    0.37
    gui
    0.37
    POSITIVE LOGITS
     prediction
    0.40
     September
    0.40
     simulation
    0.40
     l
    0.38
     smile
    0.38
     City
    0.38
     sentence
    0.38
     clue
    0.37
     Southern
    0.37
     bolt
    0.36
    Activations Density 0.297%

    No Known Activations