© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 15711
    Prev
    Next
    INDEX
    Explanations

    pronouns and possessives, especially when used in phrases naming something

    oai_token-act-pair · gemini-2.0-flash

    mentions name

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     names
    -2.77
     name
    -2.75
     Name
    -2.63
     Names
    -2.61
     NAME
    -2.50
    name
    -2.47
     named
    -2.42
     NAMES
    -2.39
    names
    -2.39
    Name
    -2.39
    POSITIVE LOGITS
    клопе
    0.36
    áda
    0.34
    惑
    0.33
     
    0.32
    knex
    0.32
    ()):
    0.31
     tu
    0.30
    ']:
    0.29
    runApp
    0.28
     a
    0.27
    Activations Density 1.242%

    No Known Activations