© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 2435
    Prev
    Next
    INDEX
    Explanations

    C++ code snippets including function definitions, comments, and other code elements

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    RegressionTest
    -0.69
    <bos>
    -0.58
    уда
    -0.57
    DateTimeField
    -0.56
    
    -0.55
    SeekBar
    -0.55
    posedge
    -0.51
    oneg
    -0.51
    出版年
    -0.51
    Бахар
    -0.48
    POSITIVE LOGITS
    moveToFirst
    0.49
     climatique
    0.49
    ellido
    0.46
    Segoe
    0.46
     capito
    0.46
     mxArray
    0.44
     оригіналу
    0.44
     manifeste
    0.43
    czegó
    0.43
     betweenstory
    0.43
    Activations Density 1.595%

    No Known Activations