© 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
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11339
    Prev
    Next
    INDEX
    Explanations

    academic texts about historical documents, research, and trials

    oai_token-act-pair · gemini-2.0-flash

    terms associated with research and documentation

    np_token-act-pair-logits · gpt-4o-mini

    research

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    IonicModule
    -0.62
     opérateur
    -0.54
    ViewImports
    -0.51
    matchCondition
    -0.48
    AutoScaleMode
    -0.46
    DispatchToProps
    -0.45
    hless
    -0.45
    Diwedd
    -0.43
    fjspx
    -0.43
    WithIdentifier
    -0.43
    POSITIVE LOGITS
     interviews
    0.84
     correspondence
    0.74
     research
    0.71
     propOrder
    0.67
     interview
    0.65
     recordings
    0.64
     writings
    0.60
    correspond
    0.60
     archival
    0.60
    RESEARCH
    0.59
    Activations Density 12.130%

    No Known Activations