© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11094
    Prev
    Next
    INDEX
    Explanations

    mentions of genes and proteins as well as their functions

    oai_token-act-pair · gemini-2.0-flash

    coding/encoding

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    Bioaccumulative
    -0.43
     Conclusions
    -0.40
    ,
    -0.40
    ?
    -0.40
     sus
    -0.37
     tủ
    -0.37
     entra
    -0.37
     centrifug
    -0.36
    Planta
    -0.36
     este
    -0.36
    POSITIVE LOGITS
    NameInMap
    0.96
     AssemblyTitle
    0.90
    parsedMessage
    0.86
    Hochspringen
    0.84
     Савезне
    0.84
     ujednoznacz
    0.84
     autorytatywna
    0.81
     Efq
    0.80
     MonoBehaviour
    0.79
    XmlAccessorType
    0.78
    Activations Density 2.058%

    No Known Activations