© 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. 5087
    Prev
    Next
    INDEX
    Explanations

    scientific citations

    oai_token-act-pair · gemini-2.0-flash

    tokens related to technical or scientific references

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

    Scientific publications

    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
     Roskov
    -0.63
    fiore
    -0.59
    AddTagHelper
    -0.56
     NavController
    -0.56
    BrowserModule
    -0.54
    UnusedPrivate
    -0.53
     للاسماء
    -0.53
     JAXB
    -0.52
    efeated
    -0.51
    AdapterFactory
    -0.51
    POSITIVE LOGITS
    exclusion
    0.53
    DoubleQuotes
    0.49
    Synth
    0.49
    værende
    0.47
     Expédié
    0.46
    NOPQRST
    0.46
     Org
    0.46
     fieltro
    0.46
    .*")]
    0.45
    XmlAccessorType
    0.44
    Activations Density 1.436%

    No Known Activations