© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 218789
    Prev
    Next
    INDEX
    Explanations

    royal imperial

    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_47_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
    нный
    0.39
    Ἡ
    0.39
    beth
    0.38
    𝑛
    0.38
     这个
    0.38
    inale
    0.37
    ⼈
    0.36
     اﻻ
    0.36
    нным
    0.36
     Spicer
    0.36
    POSITIVE LOGITS
    żyt
    0.40
     kons
    0.37
     Kus
    0.37
    滿
    0.37
    excerpt
    0.35
     kro
    0.34
    Brother
    0.34
     kakak
    0.34
    izes
    0.34
    দক্ষ
    0.34
    Activations Density 0.000%

    No Known Activations