© 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. 9413
    Prev
    Next
    INDEX
    Explanations

    "and" followed by a word

    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
     Hague
    0.32
     humide
    0.32
     শরণ
    0.32
     Suu
    0.30
    oyle
    0.29
     बुद्ध
    0.29
    讧
    0.29
     Andre
    0.28
     преде
    0.28
     IONS
    0.28
    POSITIVE LOGITS
     mill
    0.33
     además
    0.31
    𝑡
    0.31
    ственные
    0.30
    Dod
    0.30
    oljš
    0.30
     bow
    0.30
    waarden
    0.30
     hat
    0.29
    izawa
    0.29
    Activations Density 0.382%

    No Known Activations