© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 10135
    Prev
    Next
    INDEX
    Explanations

    code and other programming constructs, particularly related to C++, PHP, and dictionary compilation.

    oai_token-act-pair · gemini-2.0-flash

    头的

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    的
    -0.85
    の
    -0.66
    <bos>
    -0.57
     的
    -0.52
    oredCriteria
    -0.48
     の
    -0.47
    mui
    -0.44
    ial
    -0.43
    的面
    -0.42
    的不
    -0.41
    POSITIVE LOGITS
     resourceCulture
    0.74
     ddelweddau
    0.74
    ברס
    0.69
    EndProject
    0.69
    queryInterface
    0.68
    EndGlobalSection
    0.67
    CompleteListener
    0.66
     nakalista
    0.66
    mapStateToProps
    0.65
    brainly
    0.65
    Activations Density 7.745%

    No Known Activations