© 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
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 10830
    Prev
    Next
    INDEX
    Explanations

    the word "Flash", especially in the context of software or operating systems

    oai_token-act-pair · gemini-2.0-flash

    flash

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     flash
    -1.46
    flash
    -1.34
     Flash
    -1.23
     FLASH
    -1.22
    Flash
    -1.22
     storm
    -1.16
    FLASH
    -1.13
     STORM
    -1.09
    storm
    -1.06
     Storm
    -1.05
    POSITIVE LOGITS
     hoffe
    0.56
    发表于
    0.48
     vélos
    0.46
     дописавши
    0.45
     undone
    0.44
     répar
    0.42
     doInBackground
    0.42
     carrés
    0.42
    getVar
    0.41
    sikal
    0.40
    Activations Density 0.685%

    No Known Activations