© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 2976
    Prev
    Next
    INDEX
    Explanations

    themes related to being lost including memory loss, dreams, and being disconnected.

    oai_token-act-pair · gemini-2.0-flash

    identity and heritage

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    lahan
    -0.48
    Obrázky
    -0.43
     jScrollPane
    -0.42
     soft
    -0.42
     summarize
    -0.42
     שוליים
    -0.42
    ద్
    -0.41
    ifrance
    -0.41
    elsa
    -0.41
    同盟
    -0.41
    POSITIVE LOGITS
    ThroughAttribute
    0.73
    Бахар
    0.70
    AddTagHelper
    0.70
    WithIOException
    0.70
    تقاوى
    0.69
     незавершена
    0.68
     ComVisible
    0.63
    RegressionTest
    0.62
     AssemblyVersion
    0.60
    ValueGeneration
    0.60
    Activations Density 1.659%

    No Known Activations