© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6389
    Prev
    Next
    INDEX
    Explanations

    reflexive pronouns

    oai_token-act-pair · gemini-2.0-flash

    Reflexive pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     Curious
    -0.72
    ipients
    -0.72
    orgeous
    -0.68
     samot
    -0.67
     gata
    -0.66
    ⓘ
    -0.66
     Else
    -0.66
    Curious
    -0.65
     optimisation
    -0.64
    ouple
    -0.64
    POSITIVE LOGITS
    انجليز
    0.68
    GEBURTSDATUM
    0.65
     about
    0.57
    щото
    0.56
     ویکی‌پدیا
    0.55
     selaku
    0.54
     زیرا
    0.54
     Amérique
    0.52
     and
    0.52
     bahwa
    0.51
    Activations Density 0.057%

    No Known Activations