© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 33496
    Prev
    Next
    INDEX
    Explanations

    mango milkshake

    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_3_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
    t
    0.71
     ταιν
    0.59
     simplices
    0.58
     differentiates
    0.54
     თუ
    0.53
    endedores
    0.52
     ချ
    0.52
     consommateurs
    0.52
     progressivement
    0.52
     cần
    0.51
    POSITIVE LOGITS
    ي
    1.16
    ে
    1.10
    i
    0.98
    ed
    0.86
    י
    0.82
    as
    0.75
    ी
    0.74
    at
    0.72
    og
    0.72
    erie
    0.70
    Activations Density 0.008%

    No Known Activations