© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 154594
    Prev
    Next
    INDEX
    Explanations

    Indian tax and finance

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     j
    0.66
     J
    0.62
     ज
    0.54
     झा
    0.53
     جھ
    0.53
     ج
    0.51
     ঝ
    0.50
    J
    0.45
     ജ
    0.44
     تھ
    0.44
    POSITIVE LOGITS
     담
    0.46
     b
    0.45
     gira
    0.43
     ди
    0.43
     ब
    0.42
    달
    0.42
    Dam
    0.42
    oria
    0.41
     Dall
    0.40
     б
    0.39
    Activations Density 0.001%

    No Known Activations