© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11999
    Prev
    Next
    INDEX
    Explanations

    Java code syntax

    oai_token-act-pair · gemini-2.0-flash

    Less than symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    følgelig
    -0.63
    🏻‍♀️
    -0.59
     فريبيس
    -0.56
    Abitanti
    -0.56
    kungen
    -0.53
    yanka
    -0.52
    /*
    -0.52
    DateTimeField
    -0.50
    gdala
    -0.50
    glTranslatef
    -0.50
    POSITIVE LOGITS
    typeparam
    0.57
     Wikimedijinoj
    0.56
    ecore
    0.54
     EdgeInsets
    0.52
    oflu
    0.51
     collateral
    0.51
    memoized
    0.50
    atisk
    0.50
    ANIEL
    0.48
     оригіналу
    0.48
    Activations Density 1.360%

    No Known Activations