© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11265
    Prev
    Next
    INDEX
    Explanations

    job advertisements

    oai_token-act-pair · gemini-2.0-flash

    Jobs and offers

    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
    testens
    -0.66
    AtIndexPath
    -0.62
    hesus
    -0.54
    MatButtonModule
    -0.53
    SBATCH
    -0.52
    itattu
    -0.52
    cshtml
    -0.52
    RegistryLite
    -0.52
    uomo
    -0.51
    cinogenicity
    -0.51
    POSITIVE LOGITS
     HR
    0.57
    XmlAccessorType
    0.56
     بيها
    0.55
    ItemBackground
    0.54
     BrowserModule
    0.52
     урна
    0.52
    audiovisuel
    0.52
    Hunt
    0.50
     دیکھیے
    0.50
     PTO
    0.48
    Activations Density 2.387%

    No Known Activations