© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 170276
    Prev
    Next
    INDEX
    Explanations

    crinkling spreading stretching

    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_20_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
     wireless
    0.46
     اولیه
    0.46
     NLR
    0.44
     બો
    0.44
     NV
    0.44
     longest
    0.43
     Bolo
    0.43
    ∨
    0.43
    刷新
    0.42
     коды
    0.42
    POSITIVE LOGITS
    ítulos
    0.47
    ルメ
    0.47
    imarães
    0.46
    ס
    0.46
    Política
    0.44
    Với
    0.44
    祝
    0.44
     seguirá
    0.43
    riterien
    0.42
     כך
    0.41
    Activations Density 0.003%

    No Known Activations