© 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. 5978
    Prev
    Next
    INDEX
    Explanations

    pronouns followed by the verb "said" or "says."

    oai_token-act-pair · gemini-2.0-flash

    Pronouns in spoken dialogue

    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
     Efq
    -1.61
     Monfieur
    -1.48
     myſelf
    -1.37
     Theſe
    -1.33
     leaſt
    -1.32
     whoſe
    -1.29
     auffi
    -1.29
     photolibrary
    -1.28
     ainfi
    -1.27
     himſelf
    -1.27
    POSITIVE LOGITS
    ↵↵
    1.50
    ↵
    1.34
    <eos>
    1.19
     She
    1.10
     It
    1.02
     
    0.98
     The
    0.97
     He
    0.96
    ↵↵↵
    0.91
    The
    0.90
    Activations Density 0.986%

    No Known Activations