© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 7994
    Prev
    Next
    INDEX
    Explanations

    server

    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_40_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
    öp
    0.40
     coaches
    0.38
    submenu
    0.37
     aerobic
    0.36
     मानदंड
    0.36
    sub
    0.35
     黄
    0.35
    队伍
    0.35
     FRO
    0.35
     đòi
    0.35
    POSITIVE LOGITS
     server
    1.78
     Server
    1.70
    Server
    1.66
    server
    1.63
     SERVER
    1.48
    サーバー
    1.44
     сервер
    1.41
     서버
    1.38
    SERVER
    1.34
    服务器
    1.34
    Activations Density 0.341%

    No Known Activations