© 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
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 1778
    Prev
    Next
    INDEX
    Explanations

    phrases related to everyday inventions like traffic cones and napkins.

    oai_token-act-pair · gemini-2.0-flash

    factual snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     EClass
    -0.52
     Torn
    -0.52
    wem
    -0.49
    ()?;
    -0.47
    τού
    -0.47
    mtr
    -0.46
    pol
    -0.46
    lavi
    -0.46
    fal
    -0.46
    Personendaten
    -0.45
    POSITIVE LOGITS
     للاسماء
    0.79
    PointerException
    0.74
    ArrowToggle
    0.71
    <bos>
    0.68
    SUCCEEDED
    0.60
    AccessorTable
    0.60
     وتسجيلات
    0.59
    CodedInputStream
    0.58
     gynhyrchwyd
    0.57
     betweenstory
    0.57
    Activations Density 42.256%

    No Known Activations