© 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. 2831
    Prev
    Next
    INDEX
    Explanations

    references to newspapers, the press, and journalism

    oai_token-act-pair · gemini-2.0-flash

    paper

    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
    xty
    -0.66
    saraba
    -0.62
     ſeveral
    -0.61
    expandindo
    -0.60
    atguigu
    -0.60
     désol
    -0.58
     transférez
    -0.57
    LabelTagHelper
    -0.57
    IndentedString
    -0.57
    AutoScaleMode
    -0.56
    POSITIVE LOGITS
     paper
    2.52
    paper
    2.33
    Paper
    2.11
     Paper
    2.09
     papers
    2.02
     PAPER
    1.93
    papers
    1.77
    PAPER
    1.75
     Papers
    1.68
    Papers
    1.63
    Activations Density 2.266%

    No Known Activations