© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 193372
    Prev
    Next
    INDEX
    Explanations

    already exposed

    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_9_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
     tournaments
    0.52
     collectives
    0.50
    b
    0.49
    j
    0.49
     libraries
    0.48
     aggressively
    0.48
    f
    0.48
     gyms
    0.48
     produksi
    0.46
     lineups
    0.46
    POSITIVE LOGITS
    ו
    0.58
    ן
    0.54
    S
    0.53
     Daytime
    0.52
     Матери
    0.49
    
    0.49
    Cryptography
    0.48
     DUN
    0.46
    ם
    0.46
    盻
    0.46
    Activations Density 0.000%

    No Known Activations