© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 100397
    Prev
    Next
    INDEX
    Explanations

    days and bad days

    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_16_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
    。
    0.44
    ပါ။
    0.43
    graphHead
    0.43
    。"
    0.42
    佹
    0.42
    症状
    0.41
     shelves
    0.41
    墙
    0.41
     mergeddata
    0.41
    著
    0.41
    POSITIVE LOGITS
     महावीर
    0.50
     τ
    0.50
     vanguard
    0.48
     hedon
    0.48
     Xeon
    0.48
     alfa
    0.47
     amistad
    0.47
     α
    0.47
     fot
    0.47
    hound
    0.47
    Activations Density 0.000%

    No Known Activations