© 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. 25-GEMMASCOPE-TRANSCODER-16K
    4. 11614
    Prev
    Next
    INDEX
    Explanations

    words and short phrases related to scientific studies, processes, and outcomes

    oai_token-act-pair · gemini-2.0-flash

    academic papers and reports

    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
     للمعارف
    -0.84
     follow
    -0.62
     leave
    -0.60
    Provide
    -0.59
     Follow
    -0.58
    follow
    -0.58
     Provide
    -0.57
     Give
    -0.57
     disappear
    -0.57
    appear
    -0.56
    POSITIVE LOGITS
     coordinate
    0.83
    coordinate
    0.70
    tagHelperRunner
    0.68
     address
    0.67
     drive
    0.66
    CloseOperation
    0.64
     Coordinate
    0.61
    drive
    0.60
    Coordinate
    0.58
     shape
    0.58
    Activations Density 8.679%

    No Known Activations