© 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. 1564
    Prev
    Next
    INDEX
    Explanations

    words related to combustion and ignition

    oai_token-act-pair · gemini-2.0-flash

    starting a fire

    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
    AutoresizingMask
    -0.65
    \{\\
    -0.65
    parsedMessage
    -0.63
    NameInMap
    -0.61
    witter
    -0.59
    lusst
    -0.58
    Хьажоргаш
    -0.57
    MemoryWarning
    -0.55
     Transparen
    -0.54
     Balk
    -0.54
    POSITIVE LOGITS
     ignition
    0.60
    ########.
    0.51
    TargetException
    0.49
     arrancar
    0.47
    ACTIV
    0.47
    AutoModerator
    0.45
    ClCompile
    0.44
     spark
    0.44
     genetic
    0.41
    ribune
    0.41
    Activations Density 1.207%

    No Known Activations