© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 5561
    Prev
    Next
    INDEX
    Explanations

    words and phrases that have something to do with science, technology, and engineering

    oai_token-act-pair · gemini-2.0-flash

    technical texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     Sensors
    -0.59
     Computer
    -0.58
    itemBuilder
    -0.56
     Sistemas
    -0.55
     Sensor
    -0.55
     Device
    -0.54
    Computer
    -0.54
     COMPUTER
    -0.54
     SENSOR
    -0.53
    COMPUTER
    -0.52
    POSITIVE LOGITS
    elemField
    0.75
     EconPapers
    0.64
     "..\..\..\
    0.55
    TURE
    0.52
    Française
    0.51
    hdashline
    0.51
    Autoritní
    0.51
    ptid
    0.50
     typelib
    0.49
    षण
    0.48
    Activations Density 6.790%

    No Known Activations