© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 28913
    Prev
    Next
    INDEX
    Explanations

    gitlab-ci.yml) stages: - deploy deploy_to_staging: stage: deploy image: ruby:3.2 script: - echo "Deploying to"

    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_40_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
     Bucc
    0.42
     leisten
    0.42
    itution
    0.42
    
    0.40
    rvGroup
    0.39
    STITUTION
    0.38
    普通の
    0.38
    ビネット
    0.38
    PanelVisual
    0.38
     wahr
    0.37
    POSITIVE LOGITS
    њ
    0.41
    вото
    0.41
    register
    0.39
    PARAMETER
    0.37
    ascii
    0.36
    hams
    0.35
    ona
    0.35
     siêu
    0.35
     REGISTER
    0.34
    max
    0.34
    Activations Density 0.000%

    No Known Activations