© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 133701
    Prev
    Next
    INDEX
    Explanations

    first permanent English settlement

    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_37_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    팽
    0.43
    Lie
    0.39
    矇
    0.38
     Xi
    0.38
    Xi
    0.36
     pickle
    0.36
    \},\
    0.36
    ၢ
    0.36
     ইউন
    0.35
    شار
    0.34
    POSITIVE LOGITS
     Plymouth
    0.49
     Jamestown
    0.48
    thel
    0.44
     pilgrims
    0.43
     pilgrim
    0.42
    筲
    0.42
     ined
    0.40
    ায়ণ
    0.38
     colonies
    0.38
     Colonies
    0.38
    Activations Density 0.001%

    No Known Activations