© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 15060
    Prev
    Next
    INDEX
    Explanations

    malicious intent, dishonest, lazy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_15_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
     ефектив
    0.45
    အနေ
    0.44
    यॉर्क
    0.43
     ⿰
    0.42
     Основ
    0.42
     অ
    0.41
     বিষ
    0.41
    陆章
    0.41
    𝑛
    0.41
     sixties
    0.40
    POSITIVE LOGITS
     lazy
    0.52
     dishonest
    0.42
    ↵
    0.40
    Lazy
    0.40
     playful
    0.39
    ेला
    0.38
      
    0.38
     Lazy
    0.37
     honest
    0.36
     dishonesty
    0.35
    Activations Density 0.099%

    No Known Activations