© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 149072
    Prev
    Next
    INDEX
    Explanations

    amended, amendments, expansions

    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_18_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
     நிகழ்ச்சி
    0.41
     colloc
    0.41
     chessboard
    0.41
     प्रक्रिया
    0.39
     parallelism
    0.38
    ोजित
    0.38
     itth
    0.37
    㞖
    0.37
     yeter
    0.36
    ；
    0.36
    POSITIVE LOGITS
    crew
    0.40
    航空
    0.40
    Crew
    0.40
    รับ
    0.40
    adim
    0.39
     এক্সপ্রেস
    0.38
     effectivement
    0.38
    resto
    0.37
    邰
    0.37
    කට
    0.36
    Activations Density 0.002%

    No Known Activations