© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 174815
    Prev
    Next
    INDEX
    Explanations

    :**

    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_24_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
     để
    0.35
     debía
    0.34
    เพื่อ
    0.34
    សម្រាប់ការ
    0.33
     для
    0.33
    ær
    0.33
     लागू
    0.33
    美味
    0.33
     还
    0.32
    Pentru
    0.32
    POSITIVE LOGITS
     regional
    0.34
     writing
    0.31
     panne
    0.31
     complex
    0.30
     prose
    0.30
     Complex
    0.29
     waiters
    0.29
     indirect
    0.29
     reflexes
    0.29
     lineups
    0.28
    Activations Density 0.009%

    No Known Activations