© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 13206
    Prev
    Next
    INDEX
    Explanations

    command line scripts and configurations

    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_15_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
    вал
    0.46
    во
    0.44
    Panel
    0.43
    ophages
    0.43
    Prop
    0.42
    U
    0.42
    㝅
    0.42
     상당
    0.42
    ルダー
    0.41
    Adj
    0.41
    POSITIVE LOGITS
    stands
    0.49
    たり
    0.47
    いろんな
    0.46
    َس
    0.46
    ras
    0.45
     декла
    0.45
    ーストラリア
    0.44
    ched
    0.44
    áz
    0.44
    ط
    0.44
    Activations Density 0.011%

    No Known Activations