© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 205546
    Prev
    Next
    INDEX
    Explanations

    had + past participle

    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
    asto
    0.65
     Oma
    0.64
    ab
    0.63
    ac
    0.62
     حالا
    0.62
    л
    0.62
    has
    0.61
    arna
    0.61
    isak
    0.61
    aya
    0.61
    POSITIVE LOGITS
    К
    0.67
     comunità
    0.66
    ः
    0.66
    ین
    0.62
    ージ
    0.62
     کا
    0.61
     biking
    0.61
     respir
    0.61
     exposición
    0.61
    万
    0.61
    Activations Density 0.011%

    No Known Activations