© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 36463
    Prev
    Next
    INDEX
    Explanations

    deceive/trick

    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
     Cholesterol
    0.37
    本店
    0.37
    益
    0.37
     DISABLED
    0.35
    小題
    0.35
     নেত
    0.34
     Continent
    0.34
     Disabled
    0.34
    стойчи
    0.34
    륭
    0.34
    POSITIVE LOGITS
     deceived
    1.43
     deceive
    1.36
    骗
    1.34
     deceiving
    1.31
     deceptive
    1.29
    欺
    1.29
    騙
    1.27
     deception
    1.26
     enga
    1.25
     deceit
    1.23
    Activations Density 0.001%

    No Known Activations