© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14046
    Prev
    Next
    INDEX
    Explanations

    code snippets with error handling and related terms like request, client, and delete

    oai_token-act-pair · gemini-2.0-flash

    code/server tracing

    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
    ValueStyle
    -0.56
     Milner
    -0.46
     asset
    -0.46
    Mojo
    -0.44
    addCriterion
    -0.44
    InputModule
    -0.44
     zanahoria
    -0.43
    ArrowToggle
    -0.43
    FragmentManager
    -0.43
    ASC
    -0.43
    POSITIVE LOGITS
    RenderAtEndOf
    0.78
    ScopeManager
    0.75
     ―――――
    0.63
     itſelf
    0.62
     بيها
    0.61
     فريبيس
    0.61
     Chwiliwch
    0.60
     Theſe
    0.60
    UrlResolution
    0.60
     Efq
    0.60
    Activations Density 4.849%

    No Known Activations