© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 62712
    Prev
    Next
    INDEX
    Explanations

    tax planning and evasion

    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_11_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
    कर्मी
    0.52
    owo
    0.50
     paw
    0.50
     appliance
    0.50
     casings
    0.50
     intricate
    0.48
     inscriptions
    0.48
     robe
    0.48
    Ů
    0.48
     r
    0.48
    POSITIVE LOGITS
     Tax
    0.76
     टैक्स
    0.75
    税务
    0.60
    税
    0.59
     Taxes
    0.58
     tax
    0.57
     Son
    0.57
    Tax
    0.57
    稅
    0.55
     Taxation
    0.54
    Activations Density 0.036%

    No Known Activations