© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 65357
    Prev
    Next
    INDEX
    Explanations

    administrative appointments

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     coated
    0.35
     upright
    0.35
     deoxy
    0.35
     metall
    0.35
     dimension
    0.35
    原理
    0.35
     ≤
    0.34
     γ
    0.34
     profile
    0.34
     ReLU
    0.33
    POSITIVE LOGITS
    administrative
    0.42
    ovation
    0.38
    iciaire
    0.37
    appointment
    0.37
    appointed
    0.36
    Administrative
    0.36
    Appointment
    0.35
     Brookings
    0.34
    伀
    0.34
    apprent
    0.34
    Activations Density 0.007%

    No Known Activations