© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 11965
    Prev
    Next
    INDEX
    Explanations

    phrases involving comparisons and going beyond something

    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
    unmodifiable
    -0.54
    ArgsConstructor
    -0.53
     veneta
    -0.52
    fortawesome
    -0.52
     kasarigan
    -0.50
    Cyfeiriadau
    -0.50
     bicchiere
    -0.49
     MutableLiveData
    -0.49
     Pozna
    -0.48
     verg
    -0.48
    POSITIVE LOGITS
     ExecuteAsync
    0.78
    TagMode
    0.74
     Signalez
    0.58
    öng
    0.57
    canestro
    0.57
     FetchType
    0.54
     "-";
    0.54
    Ótimo
    0.54
    ))=\
    0.54
    layui
    0.54
    Activations Density 0.522%

    No Known Activations