© 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. 3777
    Prev
    Next
    INDEX
    Explanations

    code snippets using javascript or c++ syntax including the for loop construction

    oai_token-act-pair · gemini-2.0-flash

    code

    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
    setVerticalGroup
    -0.73
     actionTypes
    -0.57
    BackStack
    -0.55
     ISNI
    -0.54
     thanh
    -0.54
    EndInit
    -0.53
    UserScript
    -0.52
    formik
    -0.50
    PMailer
    -0.47
     webdriver
    -0.46
    POSITIVE LOGITS
     ujednoznacz
    0.89
     Monfieur
    0.72
    دانشنامهٔ
    0.67
     myſelf
    0.62
     JOptionPane
    0.60
     ſeveral
    0.59
     AssemblyTitle
    0.58
     itſelf
    0.57
     Хоро
    0.56
     Efq
    0.56
    Activations Density 2.699%

    No Known Activations