© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 372
    Prev
    Next
    INDEX
    Explanations

    code snippets, especially JavaScript, URLs, and code-related terms

    oai_token-act-pair · gemini-2.0-flash

    string/URL

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    RuleContext
    -0.77
    abestanden
    -0.71
    ViewFeatures
    -0.70
    EndContext
    -0.70
    RectangleBorder
    -0.67
     Kolon
    -0.66
    RegistryLite
    -0.65
    esgue
    -0.63
    πον
    -0.62
    èvent
    -0.61
    POSITIVE LOGITS
    SurfaceView
    0.42
     propOrder
    0.42
    ionales
    0.41
    Bibliograf
    0.40
    Invit
    0.39
     disambiguazione
    0.38
    Tracce
    0.38
    Obrázky
    0.38
    中の
    0.37
     AssemblyTitle
    0.37
    Activations Density 3.622%

    No Known Activations