© 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. 10485
    Prev
    Next
    INDEX
    Explanations

    code-related syntax like comments, directives, and versioning

    oai_token-act-pair · gemini-2.0-flash

    "//"

    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
    SharedCtor
    -0.70
    //
    -0.70
    NameInMap
    -0.69
     Италијани
    -0.69
    SharedDtor
    -0.68
    WithIOException
    -0.57
    retanto
    -0.56
    setViewportView
    -0.54
    protoimpl
    -0.54
    AntiForgeryToken
    -0.54
    POSITIVE LOGITS
    MockMvc
    0.47
     dég
    0.47
     Europy
    0.47
    malo
    0.45
     men
    0.45
    woor
    0.45
     choices
    0.44
    InstanceState
    0.43
    JspWriter
    0.42
    Instant
    0.42
    Activations Density 1.740%

    No Known Activations