© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 10378
    Prev
    Next
    INDEX
    Explanations

    mentions of pipes in plumbing or industrial contexts

    oai_token-act-pair · gemini-2.0-flash

    pipe

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    -2.61
    pipe
    -2.41
     Pipe
    -2.34
    Pipe
    -2.14
     pipes
    -2.05
     PIPE
    -1.78
    pipes
    -1.74
     Pipes
    -1.65
     pipeline
    -1.60
     Pipeline
    -1.44
    POSITIVE LOGITS
    LabelTagHelper
    0.68
    uanto
    0.58
    دانشنامهٔ
    0.57
     particulière
    0.57
    JspWriter
    0.57
    IsContent
    0.56
    
    0.56
    帖最后由
    0.55
     createSprite
    0.55
     déput
    0.55
    Activations Density 1.266%

    No Known Activations