© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 84900
    Prev
    Next
    INDEX
    Explanations

    West 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_0_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
     an
    2.45
    在
    2.19
     in
    2.16
     في
    1.76
     в
    1.61
     be
    1.60
    та
    1.51
    は
    1.47
    ق
    1.46
    も
    1.40
    POSITIVE LOGITS
    1
    1.72
    that
    1.34
     That
    1.20
    ’
    1.13
    0
    1.12
    a
    1.10
    ্ড
    1.09
     Who
    1.08
     Tokens
    1.02
    st
    0.96
    Activations Density 0.001%

    No Known Activations