© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 11213
    Prev
    Next
    INDEX
    Explanations

    fleet managers

    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_13_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
    ডো
    0.54
    ū
    0.54
    یک
    0.52
    ک
    0.52
    ド
    0.52
    体系
    0.48
    ಜ
    0.48
    𝗰
    0.48
    ajući
    0.48
    tops
    0.47
    POSITIVE LOGITS
    en
    0.58
    SHALL
    0.57
     equipamentos
    0.54
     muebles
    0.53
     insistence
    0.52
     technische
    0.52
     gear
    0.52
     repetitive
    0.52
     repetir
    0.52
     siste
    0.52
    Activations Density 0.019%

    No Known Activations