© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 14107
    Prev
    Next
    INDEX
    Explanations

    mathematical or coding syntax

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     jadx
    -0.67
    TypedDataSet
    -0.65
    Facades
    -0.63
    énario
    -0.62
    contentLoaded
    -0.61
    expandindo
    -0.60
     nonatomic
    -0.59
     مرئيه
    -0.59
    Бахар
    -0.57
     старости
    -0.57
    POSITIVE LOGITS
     vend
    0.48
    ETT
    0.45
    ecma
    0.42
    ellant
    0.41
     Sad
    0.41
    class
    0.41
     ProtoMessage
    0.41
    κιν
    0.41
    haga
    0.40
     useDispatch
    0.40
    Activations Density 0.886%

    No Known Activations