© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 143498
    Prev
    Next
    INDEX
    Explanations

    StatefulWidget or Ortega/Harlow

    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_0_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
    ंना
    1.20
     is
    1.10
    og
    1.10
    ن
    1.09
     a
    1.08
     in
    1.07
     beak
    1.01
     ت
    0.98
    واد
    0.98
     myocard
    0.97
    POSITIVE LOGITS
    л
    1.62
    ة
    1.52
    is
    1.45
    я
    1.43
    ת
    1.43
    ло
    1.41
    ı
    1.41
    ী
    1.41
    한
    1.28
    ל
    1.27
    Activations Density 0.000%

    No Known Activations