© 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-2-2B
    3. 8-GEMMASCOPE-TRANSCODER-16K
    4. 209
    Prev
    Next
    INDEX
    Explanations

    scientific and financial terminology

    oai_token-act-pair · gemini-2.0-flash

    entropy

    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
    ↵↵
    -0.40
     hold
    -0.39
    StoryboardSegue
    -0.39
    addContainerGap
    -0.38
     bolas
    -0.38
    astify
    -0.35
     tre
    -0.35
     vol
    -0.35
    DSC
    -0.34
     ред
    -0.34
    POSITIVE LOGITS
     myſelf
    0.87
     disambiguazione
    0.84
     itſelf
    0.82
     himſelf
    0.73
    ſelf
    0.72
     themſelves
    0.72
    StructEnd
    0.72
    parsedMessage
    0.69
    theoremstyle
    0.68
    addCriterion
    0.68
    Activations Density 19.481%

    No Known Activations