© 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. 139666
    Prev
    Next
    INDEX
    Explanations

    Administration access

    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
    掙
    0.38
     Bade
    0.38
    鼓
    0.38
    DEPTH
    0.38
    _{-}
    0.37
    adau
    0.37
     figura
    0.37
    dal
    0.36
     wszel
    0.36
    挣
    0.36
    POSITIVE LOGITS
    ři
    0.42
     ADMINISTRATION
    0.40
     li
    0.39
     Access
    0.39
    Sat
    0.39
    Access
    0.38
    Executives
    0.37
    Leonard
    0.37
     consumer
    0.37
     access
    0.36
    Activations Density 0.000%

    No Known Activations