© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 20425
    Prev
    Next
    INDEX
    Explanations

    start

    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_56_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
    諄
    0.39
     Tag
    0.38
     преодо
    0.36
     सिक्योर
    0.35
     ఇన్
    0.35
     спра
    0.34
     તૈયાર
    0.34
     overcoming
    0.34
     TAG
    0.34
     %>'
    0.34
    POSITIVE LOGITS
    开始
    1.07
    開始
    1.06
    Beginning
    0.99
     beginning
    0.98
     Beginn
    0.98
     শুরু
    0.98
     Beginning
    0.96
    Begin
    0.96
    เริ่ม
    0.95
    Start
    0.94
    Activations Density 0.000%

    No Known Activations