© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 29767
    Prev
    Next
    INDEX
    Explanations

    time travel and spacetime manipulation

    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_40_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
     cov
    0.47
     acciones
    0.45
     inser
    0.44
     covariance
    0.43
     covari
    0.42
     Cov
    0.42
    ভান
    0.41
     ACTIONS
    0.41
     번
    0.39
     機能
    0.39
    POSITIVE LOGITS
    Li
    0.42
     Marg
    0.40
    脱毛
    0.38
     प्रोटे
    0.38
     horrid
    0.36
    Oct
    0.36
     зерка
    0.36
     Mirror
    0.35
    Chúc
    0.35
     Li
    0.35
    Activations Density 0.032%

    No Known Activations