© 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. 198072
    Prev
    Next
    INDEX
    Explanations

    tattoo artist styles

    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
    兼容
    0.34
     palin
    0.34
     آف
    0.34
     principalement
    0.32
     surtout
    0.32
    锛
    0.32
     गुंतवणूक
    0.32
    iation
    0.32
     घास
    0.32
    莆
    0.32
    POSITIVE LOGITS
     interview
    0.39
     swagger
    0.36
     Diario
    0.34
     cutting
    0.33
     denied
    0.33
     R
    0.32
     drafted
    0.32
     maiden
    0.32
     McDermott
    0.32
     Interview
    0.32
    Activations Density 0.000%

    No Known Activations