© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 26683
    Prev
    Next
    INDEX
    Explanations

    court, testimony, evidence, documentation

    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_40_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
    PublicKey
    0.43
    ้าน
    0.39
    Revelation
    0.38
     छवियों
    0.37
     публика
    0.37
    }|^{
    0.36
    Disposition
    0.35
    Disclosure
    0.35
     அதிச
    0.35
    тивность
    0.35
    POSITIVE LOGITS
    德
    0.43
    采访
    0.39
    ᴅ
    0.37
     Order
    0.36
     Feature
    0.36
     Owen
    0.36
    Owen
    0.35
     features
    0.35
     října
    0.35
     dø
    0.34
    Activations Density 0.043%

    No Known Activations