© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 203687
    Prev
    Next
    INDEX
    Explanations

    triggers

    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_56_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
     우리
    0.44
    Objectives
    0.40
     intentions
    0.40
     दिखने
    0.39
     நம்
    0.38
    우리
    0.38
     שלנו
    0.38
     Manners
    0.37
    디
    0.37
     vengono
    0.36
    POSITIVE LOGITS
     decision
    0.65
    decision
    0.58
    Decision
    0.56
     Decision
    0.53
    trigger
    0.50
     trigger
    0.49
     triggered
    0.46
     triggers
    0.45
     Trigger
    0.45
    triggered
    0.43
    Activations Density 0.006%

    No Known Activations