© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12887
    Prev
    Next
    INDEX
    Explanations

    content discussing domain names, DNS records, and other internet technologies

    oai_token-act-pair · gemini-2.0-flash

    Computer/internet-related content

    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
     ostavi
    -0.76
    FXML
    -0.72
     intptr
    -0.71
    OGND
    -0.69
    ništ
    -0.66
    Obrázky
    -0.64
    principalColumn
    -0.64
    BASEPATH
    -0.63
    formik
    -0.61
    CppCodeGen
    -0.59
    POSITIVE LOGITS
     accett
    0.58
    Tech
    0.57
     noires
    0.57
     dovuto
    0.54
     Tech
    0.53
    ///</
    0.52
     riuscito
    0.50
     résist
    0.50
     resistenza
    0.50
    tometer
    0.49
    Activations Density 3.252%

    No Known Activations