© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 251252
    Prev
    Next
    INDEX
    Explanations

    cool

    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
     well
    0.69
     Well
    0.62
     bien
    0.58
     WELL
    0.58
    Well
    0.57
    well
    0.55
     잘
    0.52
    よく
    0.50
    WELL
    0.48
     Lets
    0.47
    POSITIVE LOGITS
    cool
    0.55
    Cool
    0.46
    sus
    0.42
     cool
    0.41
     coolest
    0.40
    kyt
    0.39
    aniu
    0.38
    墊
    0.38
    ernate
    0.38
    jších
    0.37
    Activations Density 0.022%

    No Known Activations