© 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. 217114
    Prev
    Next
    INDEX
    Explanations

    retriever, on, number, twenty

    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
     හර
    0.50
    ।
    0.49
    र्वे
    0.47
     glows
    0.47
     forested
    0.46
    。
    0.45
    ।*
    0.45
     laughs
    0.45
    dirs
    0.45
     hearts
    0.43
    POSITIVE LOGITS
    薊
    0.52
     Potsdam
    0.51
    茼
    0.49
     ger
    0.49
    批量
    0.49
    kel
    0.48
    Ger
    0.46
    ura
    0.46
    Um
    0.45
    JDK
    0.45
    Activations Density 0.000%

    No Known Activations