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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 10-GEMMASCOPE-2-TRANSCODER-262K
    4. 48739
    Prev
    Next
    INDEX
    Explanations

    conjunctions followed by names

    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_10_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
    er
    0.86
    in
    0.82
    ed
    0.80
    at
    0.76
    ς
    0.76
    es
    0.75
     och
    0.73
    и
    0.73
     le
    0.71
    a
    0.70
    POSITIVE LOGITS
    ORDON
    0.85
     QuantityOnHand
    0.79
     შეგი
    0.76
    Butyl
    0.75
    removing
    0.75
     চৈতন্ত
    0.73
    Decedent
    0.72
    waterslide
    0.70
     Ettha
    0.70
    Fmat
    0.70
    Activations Density 0.004%

    No Known Activations