© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 52354
    Prev
    Next
    INDEX
    Explanations

    cheat, scam, 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_55_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
     мо
    0.51
     Мо
    0.42
     사
    0.38
     Raid
    0.36
    ivore
    0.35
     Punt
    0.34
     সা
    0.34
    Ƣ
    0.34
     Insect
    0.34
     Clerk
    0.33
    POSITIVE LOGITS
     sw
    2.36
    sw
    1.59
    Sw
    1.48
     Sw
    1.45
     con
    1.13
     cheat
    1.05
     cheating
    0.98
     स्व
    0.98
     cheated
    0.97
     swatch
    0.96
    Activations Density 0.036%

    No Known Activations