© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5413
    Prev
    Next
    INDEX
    Explanations

    instances of "CD" followed by a number, which often relates to cell types or disease markers in scientific or medical contexts

    oai_token-act-pair · gemini-2.0-flash

    CD

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    SuppressMessage
    -0.57
    instancetype
    -0.56
    saraba
    -0.52
    ⓧ
    -0.52
    mantel
    -0.51
    maglia
    -0.50
     comigo
    -0.50
    jface
    -0.47
    TabStop
    -0.47
    nals
    -0.47
    POSITIVE LOGITS
    ########.
    0.61
    RunAsync
    0.57
    parsedMessage
    0.57
    CloseOperation
    0.54
    HostException
    0.52
    ormais
    0.50
    inaison
    0.50
    guten
    0.49
     IBOutlet
    0.48
    Expedia
    0.48
    Activations Density 0.577%

    No Known Activations