© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 218286
    Prev
    Next
    INDEX
    Explanations

    communication technology

    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_47_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
     call
    3.06
    call
    2.86
    Call
    2.78
     Call
    2.77
     CALL
    2.38
    CALL
    2.31
     कॉल
    1.98
    呼
    1.87
     calls
    1.78
     Calls
    1.70
    POSITIVE LOGITS
     mathsize
    0.38
    ่ง
    0.37
     JMJD
    0.36
    PlatformTarget
    0.35
     furrow
    0.35
     инг
    0.35
    滢
    0.35
    toUpperCase
    0.34
    ષ્ટ
    0.34
    😇
    0.34
    Activations Density 0.001%

    No Known Activations