© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 63890
    Prev
    Next
    INDEX
    Explanations

    confirmed laboratory

    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_41_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
     Grig
    0.39
    Fate
    0.39
     fate
    0.39
     Fate
    0.37
     âge
    0.37
    स्पिटल
    0.37
    端口
    0.36
    棍
    0.36
     Age
    0.36
     age
    0.35
    POSITIVE LOGITS
     confirmed
    0.88
    confirmed
    0.83
     laboratory
    0.81
     лаборатор
    0.80
    Confirmed
    0.79
    laboratory
    0.76
    Laboratory
    0.75
     confirmé
    0.74
     Laboratory
    0.73
     confirmó
    0.65
    Activations Density 0.001%

    No Known Activations