© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 192403
    Prev
    Next
    INDEX
    Explanations

    names of people and places

    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_4_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
    ার
    0.12
    ి
    0.11
    ুতি
    0.11
    ة
    0.11
    ле
    0.10
    يلا
    0.09
    angor
    0.09
    ang
    0.09
    ي
    0.09
    י
    0.09
    POSITIVE LOGITS
    o
    0.13
    do
    0.12
    you
    0.11
    dır
    0.11
    et
    0.11
    da
    0.11
    n
    0.10
    ’)
    0.10
    a
    0.10
    no
    0.10
    Activations Density 0.000%

    No Known Activations