© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 61633
    Prev
    Next
    INDEX
    Explanations

    tear down / tear off

    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_11_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     diminue
    0.67
     accentuate
    0.61
     illuminate
    0.60
     অনুবাদ
    0.59
     diminishes
    0.59
     youll
    0.56
    楶
    0.55
     감소
    0.55
    Lucy
    0.54
     ඔබේ
    0.54
    POSITIVE LOGITS
    م
    0.71
     "
    0.63
    ت
    0.59
    /**
    0.57
    ä
    0.56
      
    0.55
    <b>
    0.55
    orong
    0.54
     (
    0.54
    ↵
    0.52
    Activations Density 0.000%

    No Known Activations