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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8572
    Prev
    Next
    INDEX
    Explanations

    text from US law and legal documents, especially related to housing and discrimination

    oai_token-act-pair · gemini-2.0-flash

    legal/government documents

    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
    ValueStyle
    -0.79
    ConstraintMaker
    -0.77
    ագրություններ
    -0.62
    GEBURTSDATUM
    -0.56
    Atsauces
    -0.54
    URLException
    -0.54
     LoggerFactory
    -0.52
     muualla
    -0.52
     Sandal
    -0.52
    colhead
    -0.50
    POSITIVE LOGITS
     <>",
    0.58
     engraçadas
    0.50
     desertcart
    0.49
     pareti
    0.47
    featureID
    0.47
    국의
    0.47
    ğaz
    0.47
    >--}}
    0.46
    Cj
    0.46
     enfance
    0.46
    Activations Density 3.761%

    No Known Activations