© 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. 703
    Prev
    Next
    INDEX
    Explanations

    private health insurance

    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
    適用
    0.37
     Face
    0.37
     Delivering
    0.37
     [<
    0.36
    delivered
    0.36
     বিভাগের
    0.36
     Guam
    0.36
     Delivered
    0.36
    ணர்
    0.35
     Idaho
    0.35
    POSITIVE LOGITS
    Private
    0.93
     private
    0.91
     prywat
    0.83
    私
    0.82
     Private
    0.82
    private
    0.80
     privato
    0.79
     निजी
    0.78
     प्राइवेट
    0.78
     privati
    0.72
    Activations Density 0.005%

    No Known Activations