© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 203671
    Prev
    Next
    INDEX
    Explanations

    linear

    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_46_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
     nghĩ
    0.42
    ₂(
    0.41
     پیم
    0.39
    葙
    0.39
     carts
    0.38
    懿
    0.37
     dummy
    0.37
    𝑍
    0.37
     شیر
    0.36
     saddles
    0.36
    POSITIVE LOGITS
    ∫
    0.41
     crucial
    0.38
     aerobic
    0.37
    원의
    0.36
    tel
    0.36
     blessed
    0.35
    incu
    0.34
     Mende
    0.34
     import
    0.34
    ascii
    0.34
    Activations Density 0.001%

    No Known Activations