© 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. 12117
    Prev
    Next
    INDEX
    Explanations

    text related to football, especially player positions and play analysis

    oai_token-act-pair · gemini-2.0-flash

    programming language keywords

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

    on

    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
    setBlock
    -0.50
    createStatement
    -0.46
    assertArray
    -0.43
     defaultstate
    -0.42
    emic
    -0.42
    band
    -0.42
    mistic
    -0.42
    โลก
    -0.41
    IContainer
    -0.41
     Band
    -0.41
    POSITIVE LOGITS
    NameInMap
    0.66
    Datuak
    0.63
    abestanden
    0.63
     resourceCulture
    0.61
    :✨
    0.60
     CanadaChoose
    0.57
     mergeFrom
    0.57
     препратки
    0.57
    InjectAttribute
    0.56
     Rosewood
    0.56
    Activations Density 0.326%

    No Known Activations