© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 10040
    Prev
    Next
    INDEX
    Explanations

    expensive and time-consuming

    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
    kD
    0.38
    梓
    0.35
     возраст
    0.34
    }());
    0.34
    烁
    0.34
    🥥
    0.34
    Stere
    0.34
    महल
    0.34
    ksh
    0.34
    葷
    0.33
    POSITIVE LOGITS
     time
    1.06
    時間
    1.03
     Time
    1.01
     시간
    0.98
    时间和
    0.96
    Time
    0.94
    时间
    0.93
    time
    0.92
     時間
    0.92
     money
    0.91
    Activations Density 0.188%

    No Known Activations