© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14811
    Prev
    Next
    INDEX
    Explanations

    statistical analyses like ANOVA and instances of p-values indicating statistically significant results

    oai_token-act-pair · gemini-2.0-flash

    statistical significance

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    Show
    -0.55
     Show
    -0.50
    show
    -0.49
     show
    -0.41
    lardır
    -0.40
     sabar
    -0.39
    iverr
    -0.39
    SHOW
    -0.39
    قط
    -0.39
    ificar
    -0.39
    POSITIVE LOGITS
     насељу
    0.96
    новниш
    0.92
    GEBURTSDATUM
    0.91
     defaultstate
    0.90
    tagHelperRunner
    0.90
    TypedDataSet
    0.88
    abestanden
    0.85
    KURZBESCHREIBUNG
    0.80
    WebVitals
    0.79
    queryInterface
    0.79
    Activations Density 4.471%

    No Known Activations