© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 136111
    Prev
    Next
    INDEX
    Explanations

    live your life

    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_12_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
     時
    0.56
     Tijdens
    0.53
     loaned
    0.52
     době
    0.52
    鸦
    0.50
     prohib
    0.49
    ți
    0.47
     citizenry
    0.47
     notable
    0.47
    רת
    0.46
    POSITIVE LOGITS
    ia
    0.69
    ie
    0.68
     искать
    0.63
    awt
    0.60
    hui
    0.58
    ?...
    0.57
    v
    0.57
     αλλά
    0.57
    !...
    0.57
    iana
    0.56
    Activations Density 0.000%

    No Known Activations