© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 4795
    Prev
    Next
    INDEX
    Explanations

    code snippets, configuration settings, references to test suites, function calls, and variable declarations, possibly within a software testing context

    oai_token-act-pair · gemini-2.0-flash

    Code and programming

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     Мексичка
    -1.98
     CreateTagHelper
    -1.85
    ConstraintMaker
    -1.83
     متعلقه
    -1.80
     betweenstory
    -1.80
    RenderAtEndOf
    -1.79
    ValueStyle
    -1.79
     bezeichneter
    -1.76
     Efq
    -1.73
    脚注の使い方
    -1.72
    POSITIVE LOGITS
    ↵↵
    1.04
     
    1.00
      
    0.99
    ,
    0.99
     (
    0.98
    </strong>
    0.94
    .
    0.93
    ↵
    0.92
    <strong>
    0.89
    <eos>
    0.85
    Activations Density 3.979%

    No Known Activations