© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 153137
    Prev
    Next
    INDEX
    Explanations

    session handling and management

    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_23_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
    配合
    0.43
    CCR
    0.39
    合
    0.38
    ደበ
    0.37
    ಂತಿ
    0.37
     Помимо
    0.37
     blamed
    0.36
    ✷
    0.36
    除了
    0.36
    ทย
    0.36
    POSITIVE LOGITS
     Docker
    0.44
     ipt
    0.43
     Coca
    0.42
     vulnerabilities
    0.41
     HSBC
    0.40
     NVIDIA
    0.39
     hectares
    0.38
     Hyundai
    0.38
     états
    0.38
     JSON
    0.38
    Activations Density 0.001%

    No Known Activations