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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 255
    Prev
    Next
    INDEX
    Explanations

    code snippets related to box models and layout calculations, especially involving padding, width, and height

    oai_token-act-pair · gemini-2.0-flash

    UI boxes (in code)

    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
     box
    -2.25
     boxes
    -2.23
     Box
    -2.23
     BOX
    -2.22
    Box
    -2.17
    box
    -2.17
    BOX
    -2.13
     Boxes
    -2.09
    boxes
    -2.08
     boxed
    -1.99
    POSITIVE LOGITS
     disambiguazione
    0.71
     ✭✭
    0.61
     asset
    0.61
    AntiForgeryToken
    0.59
     Asset
    0.57
    asset
    0.56
    
    0.56
    Asset
    0.55
    SourceChecksum
    0.55
    WindowConstants
    0.54
    Activations Density 1.826%

    No Known Activations