© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 1591
    Prev
    Next
    INDEX
    Explanations

    references to external links, URLs, and some emotional punctuation

    oai_token-act-pair · gemini-2.0-flash

    Watch video links

    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
     disambiguazione
    -1.00
    SourceChecksum
    -0.94
    GEBURTSDATUM
    -0.94
     autorytatywna
    -0.90
    RectangleBorder
    -0.89
     Савезне
    -0.88
    存于互联网档案馆
    -0.88
    ChildScrollView
    -0.88
     AssemblyProduct
    -0.88
     nahilalakip
    -0.87
    POSITIVE LOGITS
     She
    0.51
    <eos>
    0.49
     .
    0.47
    ↵↵
    0.44
     I
    0.44
     U
    0.44
     The
    0.44
     i
    0.43
     R
    0.43
    The
    0.41
    Activations Density 2.309%

    No Known Activations