© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 10385
    Prev
    Next
    INDEX
    Explanations

    a variety of tokens, but it seems to have a preference for personal anecdotes and opinions, dates, and business information

    oai_token-act-pair · gemini-2.0-flash

    many

    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
     centuries
    -0.93
     decades
    -0.91
    Years
    -0.87
     Years
    -0.86
    years
    -0.86
     decade
    -0.82
     years
    -0.78
     YEARS
    -0.78
    decade
    -0.71
     Decade
    -0.68
    POSITIVE LOGITS
     many
    2.00
    many
    1.73
    Many
    1.60
     Many
    1.57
     MANY
    1.42
     muchos
    1.34
    MANY
    1.33
     många
    1.31
     muitos
    1.28
     vielen
    1.24
    Activations Density 6.445%

    No Known Activations