© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 210643
    Prev
    Next
    INDEX
    Explanations

    Dutch oven

    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
     synchronous
    0.44
     düşük
    0.44
     lepton
    0.43
    龌
    0.43
     deployments
    0.42
     kter
    0.41
    ংলার
    0.41
     perturbative
    0.41
     Blackwell
    0.41
     offshoring
    0.40
    POSITIVE LOGITS
    ==-
    0.45
     याबाबत
    0.39
     название
    0.39
     is
    0.38
    AGA
    0.38
    ésar
    0.38
     comentário
    0.38
     شاهد
    0.37
      
    0.37
    <0xA7>
    0.37
    Activations Density 0.000%

    No Known Activations