© 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. 6063
    Prev
    Next
    INDEX
    Explanations

    dates and financial years

    oai_token-act-pair · gemini-2.0-flash

    programming-related terms or syntax

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

    annual reports

    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
     xrange
    -0.60
     Obama
    -0.55
     http
    -0.54
    Obama
    -0.54
    http
    -0.50
     Zika
    -0.49
    BeginContext
    -0.48
    <!--[
    -0.47
    ISIS
    -0.46
    HostException
    -0.45
    POSITIVE LOGITS
     resourceCulture
    0.94
     '\\;'
    0.90
    ArgsConstructor
    0.81
     disambiguazione
    0.78
     Biden
    0.76
    TikTok
    0.72
    StructEnd
    0.72
     TikTok
    0.71
    MemoryWarning
    0.70
    AsUp
    0.70
    Activations Density 0.204%

    No Known Activations