© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 161440
    Prev
    Next
    INDEX
    Explanations

    * **in** following words like **script**, **data**, **husband**, **upgrade**, **ChatGPT**

    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
    Negative Logits
    )^(
    0.43
    今
    0.37
    ^(
    0.36
    емое
    0.36
     expires
    0.35
    expiration
    0.35
     runners
    0.35
    пу
    0.34
    )(&
    0.34
    人才
    0.33
    POSITIVE LOGITS
     одном
    0.44
     ആവശ്യ
    0.38
     einem
    0.37
     בן
    0.37
     magni
    0.36
    ProductImages
    0.36
    了两
    0.36
    zeniu
    0.35
     acordo
    0.35
    simile
    0.35
    Activations Density 0.003%

    No Known Activations