© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 7368
    Prev
    Next
    INDEX
    Explanations

    ErrorAction Stop

    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
    Not in Any Lists

    No Comments

    Negative Logits
     ಅಧಿಕ
    0.41
     мощность
    0.39
     ခု
    0.38
     resisted
    0.36
     poder
    0.35
    etu
    0.35
     resist
    0.34
    榷
    0.34
    articles
    0.34
    atoon
    0.34
    POSITIVE LOGITS
     بینی
    0.35
    بینی
    0.34
     Incorpor
    0.32
     bụng
    0.31
     surrounded
    0.31
     incorporating
    0.30
    Champion
    0.30
    Fellow
    0.30
    ヨーク
    0.30
    จัย
    0.29
    Activations Density 0.000%

    No Known Activations