© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 386
    Prev
    Next
    INDEX
    Explanations

    `type="text"`, `PCI`, `PCIe`

    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_38_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
    मॉन
    0.42
     iMac
    0.41
     Macri
    0.40
     MacBook
    0.39
     мони
    0.39
     desafío
    0.38
     profesión
    0.38
    莓
    0.38
     mac
    0.38
     Fourteen
    0.38
    POSITIVE LOGITS
    ecimiento
    0.43
     مذ
    0.39
    PageIndex
    0.38
    न्तर
    0.37
     NAN
    0.36
    축
    0.36
     Lucy
    0.36
    住
    0.36
    acyj
    0.36
    青
    0.36
    Activations Density 0.020%

    No Known Activations