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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 44-GEMMASCOPE-2-TRANSCODER-262K
    4. 3691
    Prev
    Next
    INDEX
    Explanations

    cheat

    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_44_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
    limsup
    0.40
    図書館
    0.39
    フラワー
    0.38
    Wagner
    0.38
    ностью
    0.38
    샌
    0.37
    Outdoor
    0.37
    심
    0.36
    玧
    0.36
    Acet
    0.35
    POSITIVE LOGITS
     cheat
    1.09
     cheating
    0.98
     cheated
    0.97
     cheats
    0.96
    cheat
    0.95
     Cheat
    0.92
    Cheat
    0.81
     copying
    0.75
     copy
    0.71
     Copy
    0.67
    Activations Density 0.040%

    No Known Activations