© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 158979
    Prev
    Next
    INDEX
    Explanations

    trap

    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_50_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
    hob
    0.48
    HOBBIT
    0.46
    ﺣ
    0.45
    UTA
    0.44
    HOB
    0.44
    íta
    0.43
    ٹا
    0.43
    Django
    0.43
    UBE
    0.41
    טה
    0.41
    POSITIVE LOGITS
     traps
    0.90
     trap
    0.86
     trapping
    0.73
    trap
    0.71
     Trap
    0.70
     trapped
    0.68
    Trap
    0.61
    陷
    0.58
     entrap
    0.54
    罠
    0.52
    Activations Density 0.000%

    No Known Activations