© 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. 199611
    Prev
    Next
    INDEX
    Explanations

    try

    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
     опы
    0.39
    乞
    0.38
     ceremonies
    0.38
     аны
    0.37
     ಕಾರ್ಯ
    0.37
     karan
    0.37
    基础
    0.36
    พ่อ
    0.35
    engelsk
    0.35
     /\.
    0.35
    POSITIVE LOGITS
     crucial
    0.44
     chunk
    0.43
    Blo
    0.42
    blo
    0.41
    Chunk
    0.38
     blo
    0.38
     problem
    0.37
     complication
    0.37
    Block
    0.37
     dispute
    0.37
    Activations Density 0.002%

    No Known Activations