© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 2957
    Prev
    Next
    INDEX
    Explanations

    words related to software and settings being enabled or disabled

    oai_token-act-pair · gemini-2.0-flash

    on/off or enable/disable

    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
     Enabled
    -0.65
    Enabled
    -0.65
     enabled
    -0.59
     bật
    -0.56
    Disable
    -0.54
     enable
    -0.54
     activating
    -0.53
     Enable
    -0.53
     activate
    -0.52
    ENABLED
    -0.50
    POSITIVE LOGITS
     EconPapers
    0.70
    setViewportView
    0.70
    zzleHttp
    0.68
    prüche
    0.68
     stanovnika
    0.66
    iNdEx
    0.65
     '\\;'
    0.65
    makeConstraints
    0.63
     AssemblyCulture
    0.62
    MergeFrom
    0.59
    Activations Density 51.550%

    No Known Activations