© 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
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4508
    Prev
    Next
    INDEX
    Explanations

    language associated with academic research and studies

    oai_token-act-pair · gemini-2.0-flash

    technical terms or coding elements

    np_token-act-pair-logits · gpt-4o-mini

    research papers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    martial
    -0.47
     propOrder
    -0.47
    trab
    -0.47
     Trade
    -0.46
     Hun
    -0.46
    хьтан
    -0.44
    antu
    -0.43
     dä
    -0.43
     trade
    -0.43
    AnchorStyles
    -0.42
    POSITIVE LOGITS
    FXML
    0.65
    }');
    0.62
     дописавши
    0.61
    日閲覧
    0.60
    XmlAccessType
    0.59
    AxisAlignment
    0.58
    sidemargin
    0.58
    Havolalar
    0.57
     /\.
    0.57
     $_"
    0.57
    Activations Density 3.579%

    No Known Activations