© 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. 7531
    Prev
    Next
    INDEX
    Explanations

    sections of scientific papers including citations, author lists, and experimental descriptions

    oai_token-act-pair · gemini-2.0-flash

    Academic paper formatting

    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
     that
    -1.18
    .")
    -1.05
    .”)
    -1.02
    ."
    -1.00
    !"
    -0.98
    ?"
    -0.94
    !")
    -0.94
    ".
    -0.92
    !".
    -0.92
     on
    -0.92
    POSITIVE LOGITS
     enfans
    0.34
    <bos>
    0.33
     varandra
    0.29
     flesta
    0.26
     étoient
    0.26
    -------------</
    0.23
     bakgrund
    0.22
     feroit
    0.22
     verksamhet
    0.21
     dieux
    0.21
    Activations Density 59.733%

    No Known Activations