© 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. 8231
    Prev
    Next
    INDEX
    Explanations

    words related to computer processing and algorithms, sometimes identifying when things are done in parallel

    oai_token-act-pair · gemini-2.0-flash

    Comparing similar things

    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
     parallel
    -1.91
     Parallel
    -1.76
    Parallel
    -1.66
    parallel
    -1.64
     parallels
    -1.45
     paralle
    -1.44
     parallelism
    -1.41
     paralelo
    -1.38
     paralel
    -1.30
     concurrent
    -1.28
    POSITIVE LOGITS
     Audiodateien
    0.61
    醐
    0.59
    Népesség
    0.54
    #!/
    0.54
    ScopeManager
    0.52
    Життєпис
    0.52
    //
    0.52
    AutoScaleMode
    0.52
    AndGet
    0.50
    OfBirth
    0.50
    Activations Density 6.244%

    No Known Activations