© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 151650
    Prev
    Next
    INDEX
    Explanations

    ```cpp code blocks

    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_18_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
     ciep
    0.52
     für
    0.46
     για
    0.45
     separates
    0.45
     vermeiden
    0.45
    auté
    0.45
     joue
    0.44
    𝕋
    0.44
     മിക
    0.44
    
    0.44
    POSITIVE LOGITS
     দূতাবাসের
    0.53
    menus
    0.51
     बराम
    0.50
     که
    0.49
     bodega
    0.48
    RAchievement
    0.47
     bagaimana
    0.47
     ambulatory
    0.46
     pretending
    0.45
    Responses
    0.45
    Activations Density 0.002%

    No Known Activations