© 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. 8121
    Prev
    Next
    INDEX
    Explanations

    text describing DNA and genetics

    oai_token-act-pair · gemini-2.0-flash

    genetics and populations

    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
     genetic
    -2.30
     Genetic
    -2.23
     gene
    -2.20
     Gene
    -2.14
    gene
    -2.11
    Genetic
    -2.11
    Gene
    -2.09
     genetically
    -2.09
    genetic
    -2.08
     genetics
    -2.06
    POSITIVE LOGITS
     Verwaltung
    0.36
    niec
    0.34
    رام
    0.31
    muo
    0.30
    انجليز
    0.29
    ServletRequest
    0.28
     ball
    0.28
     παρά
    0.28
    emang
    0.27
    ={}
    0.27
    Activations Density 5.169%

    No Known Activations