© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 9909
    Prev
    Next
    INDEX
    Explanations

    code and database related terms

    oai_token-act-pair · gemini-2.0-flash

    conn

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    <bos>
    -1.03
     frescoes
    -0.67
     decathlon
    -0.67
     getRule
    -0.63
     cargoes
    -0.63
     sauces
    -0.62
     punctures
    -0.62
     IconData
    -0.61
     cleats
    -0.60
     liquidation
    -0.60
    POSITIVE LOGITS
     Walkover
    0.64
     geweest
    0.56
    Alternate
    0.56
    Sursa
    0.52
    Références
    0.52
     Out
    0.51
    WebServlet
    0.51
    Odkazy
    0.50
    DriverManager
    0.50
    ciech
    0.50
    Activations Density 1.292%

    No Known Activations