© 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. 11465
    Prev
    Next
    INDEX
    Explanations

    C++ code syntax, including standard library elements, class members, and memory operations

    oai_token-act-pair · gemini-2.0-flash

    auto

    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
    httphttps
    -0.97
     pleaſure
    -0.96
     '\\;'
    -0.89
    WriteAttribute
    -0.87
     myſelf
    -0.84
    ViewFeatures
    -0.82
     Normdatei
    -0.82
     iſt
    -0.80
     leaſt
    -0.79
     pinulongan
    -0.78
    POSITIVE LOGITS
    cobacterium
    0.57
     Mass
    0.53
    acro
    0.51
     Lab
    0.48
     visual
    0.48
    inhard
    0.48
     t
    0.47
    fels
    0.46
     Task
    0.46
     MediatR
    0.46
    Activations Density 2.046%

    No Known Activations