© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10979
    Prev
    Next
    INDEX
    Explanations

    terms related to medical research and legal documents

    oai_token-act-pair · gemini-2.0-flash

    Law/medical texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    -0.66
    DockStyle
    -0.59
     autorytatywna
    -0.55
    WithIOException
    -0.51
     Hypertension
    -0.49
    ::$_
    -0.49
    httphttps
    -0.46
    jell
    -0.45
    fromnode
    -0.45
    下载附件
    -0.45
    POSITIVE LOGITS
     infanti
    0.65
    astify
    0.65
    poptosis
    0.63
    visiae
    0.60
     Eocene
    0.59
    esModule
    0.58
     electorate
    0.56
     voters
    0.56
    rítica
    0.55
     Charlemagne
    0.55
    Activations Density 1.948%

    No Known Activations