© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 9040
    Prev
    Next
    INDEX
    Explanations

    chunks of computer code and related terms, especially in Java and PHP

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    ,
    -0.56
    StructEnd
    -0.55
     Seeder
    -0.48
    jface
    -0.45
     MotionEvent
    -0.45
     CURLOPT
    -0.44
     InputDecoration
    -0.44
    DoubleQuotes
    -0.44
     BoxFit
    -0.43
    »,
    -0.42
    POSITIVE LOGITS
     could
    1.00
    )>=
    0.96
     does
    0.94
     can
    0.89
    )!=
    0.89
     would
    0.88
     might
    0.85
     pouvait
    0.85
    could
    0.82
     doesnt
    0.82
    Activations Density 7.317%

    No Known Activations