© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5432
    Prev
    Next
    INDEX
    Explanations

    the word "threshold" in technical documents

    oai_token-act-pair · gemini-2.0-flash

    threshold

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    Vidite
    -1.05
     Italijani
    -0.92
     TextAppearance
    -0.80
    المكان
    -0.75
    rolid
    -0.71
     通販
    -0.71
    CardBody
    -0.68
    يكب
    -0.66
    ernacle
    -0.66
     createSprite
    -0.64
    POSITIVE LOGITS
    
    0.58
    hæng
    0.56
    
    0.54
    gero
    0.54
    StandardCharsets
    0.53
    SpringRunner
    0.52
     közül
    0.50
    ğından
    0.50
    urlpatterns
    0.50
    iaomi
    0.49
    Activations Density 0.941%

    No Known Activations