© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 127772
    Prev
    Next
    INDEX
    Explanations

    name of the

    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_37_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
     politique
    0.46
     matematika
    0.43
    嵓
    0.43
    ায়ন
    0.43
    ᓲ
    0.42
     अध्य
    0.42
     metabolismo
    0.42
     развития
    0.41
    鎊
    0.41
     Lichtenfels
    0.41
    POSITIVE LOGITS
    Fy
    0.45
    Pf
    0.39
    Rat
    0.36
    ግ
    0.36
    dim
    0.34
     delicate
    0.34
    !!!
    0.34
     finisher
    0.34
     Constance
    0.33
    Ui
    0.33
    Activations Density 0.027%

    No Known Activations