© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 127683
    Prev
    Next
    INDEX
    Explanations

    concentric circles or starting from inside

    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_37_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
     Tall
    0.40
    𝑆
    0.40
    Tall
    0.40
     IndexPath
    0.40
    गोर
    0.39
    moniker
    0.39
     المقسوم
    0.38
    坭
    0.38
     پیس
    0.37
     হক
    0.37
    POSITIVE LOGITS
     concentric
    1.72
     radial
    1.02
     inner
    1.00
     circles
    0.98
     innermost
    0.97
    radial
    0.96
     rings
    0.94
     radially
    0.93
    inner
    0.92
     circle
    0.92
    Activations Density 0.004%

    No Known Activations