© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6045
    Prev
    Next
    INDEX
    Explanations

    the word "owners"

    oai_token-act-pair · gemini-2.0-flash

    owners

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    titure
    -0.63
     was
    -0.55
    djangoproject
    -0.53
    XmlAccessorType
    -0.52
    IBAction
    -0.52
    e
    -0.50
    sterne
    -0.49
     also
    -0.49
    ه
    -0.49
     in
    -0.48
    POSITIVE LOGITS
    GEBURTSDATUM
    1.09
     cherchés
    1.01
    tagHelperRunner
    0.98
    rungsseite
    0.92
     disambiguazione
    0.89
     архивлан
    0.87
    parsedMessage
    0.86
    +:+
    0.85
    FormTagHelper
    0.85
     surla
    0.84
    Activations Density 1.117%

    No Known Activations