© 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. 23896
    Prev
    Next
    INDEX
    Explanations

    Rhode Island

    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
    Negative Logits
     Che
    0.65
     Chronicle
    0.62
     Volume
    0.62
     Mathematics
    0.62
     Sp
    0.59
     "
    0.58
     Drawings
    0.58
     Science
    0.57
     Visibility
    0.57
     Davie
    0.57
    POSITIVE LOGITS
    '
    0.94
    ސ
    0.84
    ’
    0.84
     Rhode
    0.75
    ၂
    0.74
     trabajadores
    0.73
    ル
    0.72
     as
    0.70
     좋
    0.69
     imprime
    0.68
    Activations Density 0.014%

    No Known Activations