© 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-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 2165
    Prev
    Next
    INDEX
    Explanations

    mentions of years, especially in the 1900s

    oai_token-act-pair · gemini-2.0-flash

    decades

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Waray
    -0.68
    tagHelperRunner
    -0.53
     propOrder
    -0.49
    Билгалдахарш
    -0.49
     समीक्षक
    -0.48
    脚注の使い方
    -0.47
     typelib
    -0.47
     late
    -0.46
     civils
    -0.45
    Noter
    -0.45
    POSITIVE LOGITS
     getC
    0.71
     getS
    0.65
    urlencoded
    0.60
     testSet
    0.55
    gés
    0.55
    8
    0.55
    rogène
    0.54
     testGet
    0.54
    stęp
    0.52
    e
    0.52
    Activations Density 9.363%

    No Known Activations