© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 50210
    Prev
    Next
    INDEX
    Explanations

    C++ includes and standard library

    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_30_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
     sij
    0.42
     ترین
    0.38
     menit
    0.38
     victor
    0.38
     lc
    0.37
     kast
    0.37
    émission
    0.37
    鐮
    0.37
     interpret
    0.36
     niin
    0.36
    POSITIVE LOGITS
    WiFi
    0.42
    QPushButton
    0.39
    PAM
    0.38
    স্‌
    0.38
     unambiguously
    0.38
     Сте
    0.37
     negated
    0.37
    CTest
    0.36
    处于
    0.35
     CONFIG
    0.35
    Activations Density 0.011%

    No Known Activations