© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3585
    Prev
    Next
    INDEX
    Explanations

    technical language describing scientific processes

    oai_token-act-pair · gemini-2.0-flash

    process

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     surla
    -1.00
     betweenstory
    -0.67
    elerik
    -0.67
    canestro
    -0.66
    --)
    -0.63
    ]]
    -0.63
     HasFactory
    -0.60
    ,))
    -0.59
     estimés
    -0.59
    "):
    -0.56
    POSITIVE LOGITS
     process
    3.23
    process
    2.91
     Process
    2.80
    Process
    2.59
     PROCESS
    2.42
     proceso
    2.13
    PROCESS
    1.98
     Prozess
    1.90
     processo
    1.88
     processus
    1.79
    Activations Density 10.170%

    No Known Activations