© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 216947
    Prev
    Next
    INDEX
    Explanations

    consultant physician, roles, HR

    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_16_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
     измени
    0.64
    wellery
    0.63
     waving
    0.60
     学習
    0.57
     однако
    0.56
     quedó
    0.55
     क्विंटल
    0.54
    🏧
    0.53
    </h2>
    0.52
    izontal
    0.52
    POSITIVE LOGITS
    最好
    0.53
     shim
    0.50
    Mother
    0.49
    Pot
    0.47
    uração
    0.46
     sis
    0.45
    Kafka
    0.45
    함
    0.45
    Cancer
    0.44
     phổi
    0.44
    Activations Density 0.000%

    No Known Activations