© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 5145
    Prev
    Next
    INDEX
    Explanations

    various tags used in code and data structures, such as database fields, html, json, apex, and more

    oai_token-act-pair · gemini-2.0-flash

    numbers, frequency

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    IUrlHelper
    -0.78
     Chwiliwch
    -0.75
     Савезне
    -0.69
    Chham
    -0.64
    Personendaten
    -0.63
    InvalidProtocol
    -0.61
     समीक्षाओं
    -0.61
     صوتيه
    -0.60
    
    -0.59
    SharedDtor
    -0.59
    POSITIVE LOGITS
     numbers
    0.52
     number
    0.49
    jbl
    0.46
     frequency
    0.46
     average
    0.45
     timing
    0.44
    országban
    0.43
     percentage
    0.43
     reason
    0.43
     Number
    0.42
    Activations Density 3.083%

    No Known Activations