© 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. 6483
    Prev
    Next
    INDEX
    Explanations

    first person pronouns and mentions of other people

    oai_token-act-pair · gemini-2.0-flash

    first-person perspectives and social interactions

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

    pronouns

    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
    DockStyle
    -0.84
     itſelf
    -0.82
    UnusedPrivate
    -0.81
    GEBURTSDATUM
    -0.81
    AsUp
    -0.78
     resourceCulture
    -0.77
    جغرافيا
    -0.76
    NameInMap
    -0.73
     myſelf
    -0.73
    InvalidProtocol
    -0.71
    POSITIVE LOGITS
     interface
    0.50
     met
    0.50
    chero
    0.48
     interacted
    0.47
     interact
    0.47
     interacts
    0.47
     tu
    0.46
     Good
    0.46
     Don
    0.46
    聊
    0.45
    Activations Density 1.875%

    No Known Activations