© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 248748
    Prev
    Next
    INDEX
    Explanations

    trigger

    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
    Not in Any Lists

    No Comments

    Negative Logits
     um
    0.44
     ум
    0.39
     tránh
    0.39
    ：「
    0.37
     ничек
    0.37
    -‘
    0.36
    чём
    0.36
     diurnal
    0.35
     ‘
    0.35
    わせ
    0.35
    POSITIVE LOGITS
     triggered
    0.68
     trigger
    0.66
     triggering
    0.64
     Trigger
    0.62
     triggers
    0.60
    trigger
    0.55
    triggered
    0.54
    Trigger
    0.52
    TRIGGER
    0.50
    触发
    0.49
    Activations Density 0.001%

    No Known Activations