© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 46453
    Prev
    Next
    INDEX
    Explanations

    high-level descriptions

    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_22_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
     tom
    0.23
     GB
    0.20
     bob
    0.20
     costume
    0.19
    予算
    0.19
     Mei
    0.19
     costumes
    0.19
     badges
    0.19
     buck
    0.18
     j
    0.18
    POSITIVE LOGITS
    ជំងឺ
    0.21
    áló
    0.21
    ecimento
    0.21
    |$
    0.21
    lementine
    0.21
     Старки
    0.20
    étation
    0.20
    onnage
    0.20
    र्ती
    0.20
    purecounter
    0.20
    Activations Density 0.060%

    No Known Activations