© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2889
    Prev
    Next
    INDEX
    Explanations

    a wide range of terms in technical documentation including programming and engineering

    oai_token-act-pair · gemini-2.0-flash

    programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     NSCoder
    -0.98
    ftagPool
    -0.96
    Personensuche
    -0.94
     Efq
    -0.93
     esternos
    -0.84
     وتسجيلات
    -0.81
     étoit
    -0.80
     linkovi
    -0.79
     houſe
    -0.78
    unnitel
    -0.78
    POSITIVE LOGITS
     
    0.42
    tld
    0.39
    ven
    0.37
    횟
    0.36
    
    0.36
    stdbool
    0.35
    退
    0.34
    ↵
    0.33
    sik
    0.33
     List
    0.33
    Activations Density 19.242%

    No Known Activations