© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 212135
    Prev
    Next
    INDEX
    Explanations

    dynamic DNS and IP forwarding

    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_20_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
     ബാ
    0.46
    вест
    0.45
     Symfony
    0.41
     Admission
    0.41
    мін
    0.41
     mannit
    0.41
     προσ
    0.41
    ክ
    0.41
    άρ
    0.40
     ```
    0.39
    POSITIVE LOGITS
    randomNumber
    0.46
     centerX
    0.45
    꽉
    0.43
     обратно
    0.41
    🔁
    0.41
     lưng
    0.40
    යට
    0.39
    矸
    0.39
    一路
    0.39
     fungus
    0.39
    Activations Density 0.003%

    No Known Activations