© 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. 215150
    Prev
    Next
    INDEX
    Explanations

    testng, Test, pytest

    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
    Not in Any Lists

    No Comments

    Negative Logits
    illers
    0.41
    قیه
    0.39
     বাই
    0.39
    \"",
    0.38
    ﹡
    0.38
    asel
    0.38
    0.37
    щенко
    0.37
    యన్స్
    0.37
    䐈
    0.36
    POSITIVE LOGITS
     India
    0.49
     Jawaharlal
    0.46
     Ayurveda
    0.45
     INDIA
    0.44
     jute
    0.44
     banc
    0.43
     sarees
    0.42
     salwar
    0.42
     Hindu
    0.42
     Hinduism
    0.41
    Activations Density 0.000%

    No Known Activations