© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 14427
    Prev
    Next
    INDEX
    Explanations

    programming 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_40_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
    Mac
    0.47
     mac
    0.42
     Mac
    0.42
    ców
    0.39
     iMac
    0.39
    Xcode
    0.39
    GitHub
    0.38
    mac
    0.38
    ณ
    0.38
     Codes
    0.38
    POSITIVE LOGITS
     Python
    0.57
    python
    0.56
     JavaScript
    0.54
     python
    0.53
    Python
    0.51
     Javascript
    0.47
     PYTHON
    0.45
    JavaScript
    0.45
     Browser
    0.43
     Jav
    0.43
    Activations Density 0.410%

    No Known Activations