© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12492
    Prev
    Next
    INDEX
    Explanations

    references to leadership roles and official positions within organizations

    oai_token-act-pair · gemini-2.0-flash

    terms related to authority and decision-making

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

    decision making

    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
    PreferredItem
    -0.70
    expandindo
    -0.69
    abetes
    -0.59
    ViewFeatures
    -0.59
    rungsseite
    -0.58
    oredCriteria
    -0.57
     GenerationType
    -0.57
     ExecuteAsync
    -0.56
    Espèce
    -0.54
     poveznice
    -0.54
    POSITIVE LOGITS
     decision
    1.06
    decision
    0.94
    Decision
    0.87
     Decision
    0.87
     authority
    0.82
    authority
    0.76
     Entscheid
    0.76
     DECISION
    0.75
    Decisions
    0.73
     central
    0.71
    Activations Density 2.297%

    No Known Activations