© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 121656
    Prev
    Next
    INDEX
    Explanations

    app

    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_37_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
     App
    0.55
    App
    0.55
     app
    0.50
    app
    0.49
    Applications
    0.44
    APP
    0.42
     앱
    0.42
    アプリ
    0.41
    Application
    0.41
    Apps
    0.40
    POSITIVE LOGITS
     Stanis
    0.42
    ట్టు
    0.41
     Champion
    0.41
     vapour
    0.39
     establishments
    0.39
    köy
    0.39
    ள்கள்
    0.38
     koniec
    0.38
     entsteht
    0.38
    県
    0.37
    Activations Density 0.004%

    No Known Activations