© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 5500
    Prev
    Next
    INDEX
    Explanations

    code snippets with file IO and potentially some javascript elements

    oai_token-act-pair · gemini-2.0-flash

    programming code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     оригіналу
    -0.81
    parsedMessage
    -0.77
    MessageTagHelper
    -0.75
    ⓧ
    -0.75
    IsMutable
    -0.73
    CodeAttribute
    -0.71
    Autoritní
    -0.69
    GEBURTSDATUM
    -0.68
    Népesség
    -0.66
    AutoField
    -0.64
    POSITIVE LOGITS
     BrowserModule
    0.57
    innerHeight
    0.55
    ceae
    0.52
     onCreateView
    0.51
     PhpStorm
    0.50
     imó
    0.49
    ätie
    0.48
     Bedürf
    0.48
    isempty
    0.48
     tím
    0.48
    Activations Density 1.532%

    No Known Activations