© 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. 26933
    Prev
    Next
    INDEX
    Explanations

    South Africa Africa

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Attribute
    0.43
     फेक
    0.38
    그
    0.36
    یتے
    0.36
    ικού
    0.36
    ࢮ
    0.36
     ভিত
    0.36
     महीने
    0.35
     attribute
    0.35
    鞠
    0.35
    POSITIVE LOGITS
     etat
    0.41
    amd
    0.39
    Isolated
    0.39
     pointy
    0.38
    ynchronously
    0.38
     റാ
    0.37
    terdam
    0.37
     RSA
    0.37
     noma
    0.37
    дра
    0.37
    Activations Density 0.011%

    No Known Activations