© 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. 247442
    Prev
    Next
    INDEX
    Explanations

    code delimiters and comments

    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
    дика
    0.39
     ơn
    0.38
     VOC
    0.37
    ቆ
    0.37
    لیف
    0.36
    ີ້
    0.36
    Ἱ
    0.36
     TNumber
    0.36
    ////////////
    0.36
    られている
    0.36
    POSITIVE LOGITS
     mag
    0.54
    mag
    0.51
     Mag
    0.48
    Mag
    0.47
    resel
    0.46
     مغ
    0.45
     solely
    0.44
     observed
    0.43
    ماغ
    0.42
     Com
    0.42
    Activations Density 0.000%

    No Known Activations