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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 39-GEMMASCOPE-2-TRANSCODER-262K
    4. 4012
    Prev
    Next
    INDEX
    Explanations

    summarizing key differences

    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_39_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
    ap
    0.39
     en
    0.37
     phone
    0.35
      
    0.35
    [
    0.33
    nap
    0.32
     multi
    0.32
    ↵
    0.31
     (
    0.31
    mp
    0.31
    POSITIVE LOGITS
     ойношот
    0.46
     !***
    0.41
    慫
    0.41
     வல
    0.41
    别人的
    0.39
    াল্ড
    0.39
    哳
    0.38
    ActionResult
    0.38
     سپورټ
    0.38
    лизм
    0.38
    Activations Density 0.004%

    No Known Activations