© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11229
    Prev
    Next
    INDEX
    Explanations

    the java abstract window toolkit

    oai_token-act-pair · gemini-2.0-flash

    awt

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    awt
    -1.33
    AxisAlignment
    -0.85
    FieldBuilder
    -0.70
    Tembelea
    -0.64
    BeginContext
    -0.64
    #+#
    -0.64
    OGND
    -0.63
    Slf
    -0.63
    WebVitals
    -0.63
    tagHelperRunner
    -0.60
    POSITIVE LOGITS
     betweenstory
    0.52
    AutoField
    0.44
     desvan
    0.44
     Ausführung
    0.42
    lju
    0.42
    CELLANEOUS
    0.41
    andReturn
    0.39
    Diwedd
    0.39
    løs
    0.39
     ویکی
    0.39
    Activations Density 0.167%

    No Known Activations