© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 209603
    Prev
    Next
    INDEX
    Explanations

    code loops and initialization

    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
    Not in Any Lists

    No Comments

    Negative Logits
      
    0.42
    '
    0.41
    -
    0.40
     G
    0.38
    (
    0.38
    Travel
    0.38
     -
    0.37
     F
    0.37
     (
    0.37
    yd
    0.36
    POSITIVE LOGITS
     purnama
    0.42
     партне
    0.42
     পাখ
    0.41
     йөк
    0.41
     দায়িত্ব
    0.41
     verantwoord
    0.41
     MDET
    0.40
    SpringMVCProject
    0.40
    ધાનસભા
    0.40
     જવાબ
    0.40
    Activations Density 0.003%

    No Known Activations