© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6613
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to computer servers and their performance

    oai_token-act-pair · gemini-2.0-flash

    terms associated with loading processes

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

    Server performance

    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
     FBref
    -0.56
    complexType
    -0.46
    roblast
    -0.44
     Closure
    -0.44
     Closing
    -0.41
    ropolitan
    -0.41
     solubility
    -0.39
     censi
    -0.38
     commercially
    -0.38
     incorporated
    -0.38
    POSITIVE LOGITS
     nakalista
    0.85
     load
    0.77
    load
    0.75
    HtmlAttribute
    0.71
     مشين
    0.69
    Load
    0.69
    Vidite
    0.69
     محفوظة
    0.68
     Load
    0.67
     ModelExpression
    0.66
    Activations Density 3.641%

    No Known Activations