© 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. 12722
    Prev
    Next
    INDEX
    Explanations

    scientific language related to medical research, especially genes, proteins, and diseases

    oai_token-act-pair · gemini-2.0-flash

    Numerical data in research

    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
    цездатний
    -0.50
     surla
    -0.46
    @@@@@
    -0.46
     schutz
    -0.42
     ENGINEERING
    -0.42
     entret
    -0.42
     transparentes
    -0.42
     persa
    -0.42
     desped
    -0.41
     Einfach
    -0.41
    POSITIVE LOGITS
     newOwner
    0.57
     mM
    0.57
    itoneal
    0.54
    期刊论文
    0.52
    esez
    0.52
    ˒
    0.50
    juvant
    0.50
    IndentedString
    0.49
     
    0.49
    \{\\
    0.48
    Activations Density 35.045%

    No Known Activations