© 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. 24788
    Prev
    Next
    INDEX
    Explanations

    Illusion or natural

    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
    Abstract
    0.39
     abstract
    0.39
    씻
    0.37
    المل
    0.37
     عَ
    0.37
    Фото
    0.36
     シューズ
    0.36
    꾸
    0.36
    崤
    0.36
     Kün
    0.35
    POSITIVE LOGITS
     illusion
    0.89
     natural
    0.76
     Natural
    0.71
     Illusion
    0.71
    illusion
    0.70
    Natural
    0.66
     NATURAL
    0.63
    natural
    0.63
     illusions
    0.62
     fig
    0.61
    Activations Density 0.027%

    No Known Activations