© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 205578
    Prev
    Next
    INDEX
    Explanations

    found or created

    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_56_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
     up
    0.45
     n
    0.41
     ন
    0.39
     Up
    0.39
    ":
    0.39
    up
    0.38
    น
    0.38
    Up
    0.37
     ":
    0.37
     lên
    0.37
    POSITIVE LOGITS
    ereum
    0.43
     live
    0.42
    ..)
    0.41
    ..</
    0.39
    $.)
    0.39
    ónio
    0.38
     remedial
    0.38
    ঙ্কে
    0.38
    live
    0.38
    ..
    0.37
    Activations Density 0.006%

    No Known Activations