© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 74558
    Prev
    Next
    INDEX
    Explanations

    Mandela Effect, criticisms of

    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_31_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
     Eating
    0.45
    eating
    0.41
     Inspe
    0.39
     गौ
    0.39
     eating
    0.39
    Eating
    0.38
     согла
    0.37
     pavilion
    0.37
     吃
    0.37
     file
    0.37
    POSITIVE LOGITS
    фри
    0.50
    Grid
    0.40
    Solid
    0.40
    ఫ
    0.39
    несен
    0.37
     renovating
    0.36
    Watt
    0.36
    prix
    0.36
     طريقة
    0.35
     renovate
    0.35
    Activations Density 0.000%

    No Known Activations