© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13479
    Prev
    Next
    INDEX
    Explanations

    scientific writing mentioning bacterium names and other words related to microbiology

    oai_token-act-pair · gemini-2.0-flash

    Scientific / bacterial names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     ujednoznacz
    -0.98
    SharedDtor
    -0.88
     disambiguazione
    -0.84
     autorytatywna
    -0.79
    MENAFN
    -0.77
    曖昧さ回避
    -0.76
    GOTREF
    -0.75
     Италијани
    -0.74
    XDECREF
    -0.73
     surla
    -0.72
    POSITIVE LOGITS
     var
    0.51
     olmayan
    0.45
    var
    0.41
    porre
    0.41
     AT
    0.41
    ADDITIONAL
    0.39
    itmen
    0.39
     nube
    0.38
    phoria
    0.38
    ashian
    0.38
    Activations Density 3.223%

    No Known Activations