© 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. 2532
    Prev
    Next
    INDEX
    Explanations

    parenthesis, numbers, and times

    oai_token-act-pair · gemini-2.0-flash

    delimiters

    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
     Efq
    -0.75
     Monfieur
    -0.59
     ―――――
    -0.57
     myſelf
    -0.56
     crdi
    -0.54
     Jefus
    -0.52
    ſelves
    -0.51
     doubtnut
    -0.50
    ſelf
    -0.49
     Shakspeare
    -0.49
    POSITIVE LOGITS
     estekak
    0.44
     »
    0.44
     >
    0.39
    0.39
     l
    0.38
     «
    0.37
     {
    0.37
     _
    0.37
     ta
    0.37
     />

    0.36
    Activations Density 5.700%
    No Known Activations