© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13548
    Prev
    Next
    INDEX
    Explanations

    decimal numbers or numbers in a listing

    oai_token-act-pair · gemini-2.0-flash

    statistical data and anomalous values

    np_token-act-pair-logits · gpt-4o-mini

    Identifying specific references

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    出版年
    -0.74
     otomatig
    -0.64
    mybatisplus
    -0.63
    נטרנט
    -0.62
    posedge
    -0.59
    WaitGroup
    -0.57
    getOutputStream
    -0.55
    newInstance
    -0.55
    AddTagHelper
    -0.52
    istique
    -0.52
    POSITIVE LOGITS
    SPATH
    0.59
    Bear
    0.49
    bear
    0.46
    
    0.45
    
    0.45
    Bioaccumulative
    0.45
    gige
    0.43
    bears
    0.42
     LOWER
    0.42
     mezza
    0.42
    Activations Density 2.491%

    No Known Activations