© 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. 9201
    Prev
    Next
    INDEX
    Explanations

    place names, particularly in the United States and South Africa, and sports teams

    oai_token-act-pair · gemini-2.0-flash

    White

    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
    SourceChecksum
    -0.56
    Lähteet
    -0.55
    RenderAtEndOf
    -0.54
    Thee
    -0.53
    Muri
    -0.52
    expandindo
    -0.52
    !("{}",
    -0.51
    tvguidetime
    -0.50
    Of
    -0.50
    évaluateur
    -0.50
    POSITIVE LOGITS
    <bos>
    0.43
     Court
    0.34
    time
    0.29
    if
    0.29
    side
    0.29
    set
    0.28
     Safety
    0.27
    more
    0.27
    like
    0.27
     Attack
    0.27
    Activations Density 2.556%

    No Known Activations