© 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. 235218
    Prev
    Next
    INDEX
    Explanations

    Yangtze

    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
    携带
    0.39
     Cedar
    0.39
    Exist
    0.38
     Exist
    0.38
     বাত
    0.37
    攜
    0.35
     kerap
    0.35
    携
    0.35
     हेक्टेयर
    0.34
    ْل
    0.34
    POSITIVE LOGITS
    र्देश
    0.42
     Ultim
    0.39
     amphibious
    0.38
     Chiang
    0.38
    മാർ
    0.38
    Nik
    0.38
     Thai
    0.37
     poc
    0.37
     ambition
    0.37
     По
    0.37
    Activations Density 0.000%

    No Known Activations