© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 248093
    Prev
    Next
    INDEX
    Explanations

    fool or 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_56_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    葡萄
    0.43
     RF
    0.37
    Ана
    0.36
     analog
    0.36
    стер
    0.35
     chor
    0.35
     ана
    0.35
    '></
    0.35
    hexahydro
    0.34
     orientations
    0.34
    POSITIVE LOGITS
     fool
    2.95
     Fool
    2.58
     fools
    2.48
    Fool
    2.38
     fooling
    2.33
    fool
    2.31
     Fools
    2.16
     fooled
    2.08
     trick
    1.97
     tricks
    1.78
    Activations Density 0.004%

    No Known Activations