© 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
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 13656
    Prev
    Next
    INDEX
    Explanations

    the word "type" and a few closely related words like "mode", "source," and "case"

    oai_token-act-pair · gemini-2.0-flash

    type

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    endenza
    -0.62
    AnchorStyles
    -0.61
    ณ์
    -0.61
    <bos>
    -0.59
    PerformLayout
    -0.57
     isInitialized
    -0.56
     Ny
    -0.55
    <?,
    -0.55
    ècie
    -0.54
    Wrap
    -0.54
    POSITIVE LOGITS
     exécu
    0.54
     nationaux
    0.54
    URLException
    0.52
    ContentAsync
    0.51
     propOrder
    0.51
     financières
    0.49
    cshtml
    0.49
     lửa
    0.46
    EndContext
    0.45
     fédéral
    0.45
    Activations Density 3.775%

    No Known Activations