© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 599
    Prev
    Next
    INDEX
    Explanations

    words relating to pipes and their construction/maintenance

    oai_token-act-pair · gemini-2.0-flash

    Pipes and pipelines

    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
     Pipe
    -2.19
     pipe
    -2.14
     Pipeline
    -2.06
     pipeline
    -2.05
    Pipe
    -2.03
     tube
    -2.00
     pipes
    -1.98
     PIPE
    -1.95
    pipe
    -1.95
     Pipes
    -1.95
    POSITIVE LOGITS
     Ashanti
    0.47
     للاسماء
    0.47
    krut
    0.47
    তথ্যসূত্র
    0.46
    hamshire
    0.46
     Kalyan
    0.45
    Omega
    0.45
     AWD
    0.45
     飾
    0.45
    ◆◆
    0.45
    Activations Density 2.168%

    No Known Activations