© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 237259
    Prev
    Next
    INDEX
    Explanations

    business contracts

    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_46_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
     soul
    0.43
    working
    0.41
     Soul
    0.41
     working
    0.40
     velocities
    0.38
     tang
    0.38
     Sunrise
    0.38
     material
    0.38
     sessions
    0.38
     ‘
    0.37
    POSITIVE LOGITS
    Emma
    0.43
     omfatt
    0.41
     ശബരിമല
    0.39
    資本
    0.39
     submitted
    0.39
    提交
    0.38
    submitted
    0.38
     kapit
    0.38
    ocatore
    0.38
    确认
    0.37
    Activations Density 0.000%

    No Known Activations