© 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. 4480
    Prev
    Next
    INDEX
    Explanations

    names of people, teams, cities or states, and years

    oai_token-act-pair · gemini-2.0-flash

    non-standard or misspelled terms

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

    biographical data

    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
     Linda
    -0.72
     Debbie
    -0.69
     Terry
    -0.65
     Kathy
    -0.65
     Larry
    -0.64
     Judy
    -0.64
     Gail
    -0.62
    Debbie
    -0.61
     Steve
    -0.59
     Sue
    -0.58
    POSITIVE LOGITS
    aarrggbb
    0.89
    Jeografia
    0.88
    HomeAsUpEnabled
    0.81
    oredCriteria
    0.80
    AndEndTag
    0.79
    \{\\
    0.78
    :✨
    0.76
     StatelessWidget
    0.75
    TypedDataSet
    0.74
    RepeatedField
    0.74
    Activations Density 2.040%

    No Known Activations