© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 33516
    Prev
    Next
    INDEX
    Explanations

    thanks or merci

    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_31_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
     श्रद्धांजलि
    0.40
     практику
    0.37
     සමා
    0.36
    imetric
    0.36
    ữ
    0.35
    遵循
    0.34
     పరీక్ష
    0.34
     Croatian
    0.34
     اهلا
    0.34
     అధికార
    0.34
    POSITIVE LOGITS
    鬏
    0.44
     tower
    0.40
     shar
    0.38
     unat
    0.38
    Tower
    0.37
    펠
    0.37
    CCA
    0.37
                                  
    0.36
    बर्ग
    0.35
     langt
    0.35
    Activations Density 0.001%

    No Known Activations