© 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. 12215
    Prev
    Next
    INDEX
    Explanations

    medical terminology and drug-related language, especially from message board postings

    oai_token-act-pair · gemini-2.0-flash

    Parentheses and periods

    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
     intptr
    -0.91
    DoubleQuotes
    -0.90
    èdia
    -0.86
    AddTagHelper
    -0.84
     Exactos
    -0.78
     referrerpolicy
    -0.77
    EndProject
    -0.76
    EndInit
    -0.75
     AssemblyVersion
    -0.75
    ?
    -0.74
    POSITIVE LOGITS
    <bos>
    0.51
     to
    0.42
    -
    0.41
    its
    0.39
     completo
    0.38
     обращения
    0.38
    '
    0.38
    Impl
    0.37
    لف
    0.37
    ites
    0.36
    Activations Density 0.534%

    No Known Activations