© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 218572
    Prev
    Next
    INDEX
    Explanations

    questions about how to do things

    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
    ᴬ
    0.41
     cuticle
    0.39
     cytotoxicity
    0.38
    𝕂
    0.38
     أكتوبر
    0.38
    ައި
    0.37
     transmitir
    0.37
     selectivity
    0.37
     versatility
    0.37
     cleanliness
    0.37
    POSITIVE LOGITS
     হয়েছে
    0.42
     vraag
    0.40
     gefragt
    0.39
     demandé
    0.38
     întreb
    0.38
     găsit
    0.38
     Albrecht
    0.38
     یافته
    0.37
     ([[
    0.37
     सवाल
    0.36
    Activations Density 0.001%

    No Known Activations