© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 19022
    Prev
    Next
    INDEX
    Explanations

    Japanese tattoos

    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_34_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
     ছাদে
    0.39
     kaug
    0.38
    תר
    0.38
    遠
    0.37
     सुनें
    0.36
    কাতার
    0.36
    enaire
    0.36
    远
    0.35
    softmax
    0.35
    duğu
    0.35
    POSITIVE LOGITS
     tigers
    0.46
     tiger
    0.45
     Tattoo
    0.43
     tattoo
    0.43
    Audit
    0.41
     tigre
    0.41
     leop
    0.40
     leopards
    0.40
     IBC
    0.40
    🐅
    0.40
    Activations Density 0.001%

    No Known Activations