© 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. 4814
    Prev
    Next
    INDEX
    Explanations

    first-person pronouns and contractions of "to be"

    oai_token-act-pair · gemini-2.0-flash

    various phrases starting with 'I'

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

    I

    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
    principalTable
    -0.71
    parsedMessage
    -0.53
    ⓧ
    -0.48
    RectangleBorder
    -0.47
    Abitanti
    -0.44
    署
    -0.44
    ScopeManager
    -0.43
    llary
    -0.43
    /**
    -0.42
    qvarna
    -0.41
    POSITIVE LOGITS
    ItemBackground
    0.73
    -------------</
    0.59
    AsUp
    0.57
     pageContext
    0.56
     саны
    0.56
    ĩnh
    0.55
     edelstahl
    0.54
     Dummies
    0.54
    atguigu
    0.52
     vilja
    0.52
    Activations Density 0.783%

    No Known Activations