© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 11855
    Prev
    Next
    INDEX
    Explanations

    Hartford, CT, Connecticut

    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_13_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
    ev
    0.57
     Assad
    0.56
     Louisiana
    0.54
     Angelina
    0.52
     Kurdistan
    0.52
    m
    0.52
     gacchati
    0.50
    ale
    0.50
     gale
    0.50
     ave
    0.49
    POSITIVE LOGITS
    ਕਾਰ
    0.61
    ზე
    0.60
     सेवा
    0.58
     শ্রেণীর
    0.58
    ہ
    0.58
    하며
    0.57
     ঘটনার
    0.56
    북
    0.56
     ব্যবসা
    0.55
    分野
    0.55
    Activations Density 0.000%

    No Known Activations