© 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. 40756
    Prev
    Next
    INDEX
    Explanations

    names like Walker, Reese, Simpson, Lambert, Ren, Broflovski, Mbappé

    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
    i
    0.95
    s
    0.92
    ي
    0.84
    es
    0.79
    י
    0.77
    ant
    0.76
    e
    0.75
    as
    0.74
    ed
    0.71
    en
    0.69
    POSITIVE LOGITS
    糹
    0.62
    रासायनिक
    0.62
     Analyzing
    0.61
    แมนเชสเตอร์
    0.59
    行う
    0.59
    妨
    0.59
    세요
    0.59
    おしゃれ
    0.59
    λή
    0.57
    ετε
    0.57
    Activations Density 0.000%

    No Known Activations