© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 5576
    Prev
    Next
    INDEX
    Explanations

    code syntax, likely related to object-oriented programming and possibly database interactions

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     AssemblyProduct
    -0.66
     @"/
    -0.63
     net
    -0.62
    LookAnd
    -0.59
     credit
    -0.56
     EconPapers
    -0.56
     terms
    -0.56
     payment
    -0.52
    credits
    -0.52
    credit
    -0.52
    POSITIVE LOGITS
    Hochspringen
    0.58
    PHE
    0.56
     Audiodateien
    0.53
     multiplex
    0.53
     Crusoe
    0.52
    存于互联网档案馆
    0.52
    gister
    0.52
     Buche
    0.52
     PLO
    0.52
     Lynda
    0.50
    Activations Density 0.409%

    No Known Activations