© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 4830
    Prev
    Next
    INDEX
    Explanations

    HTML code and code snippets

    oai_token-act-pair · gemini-2.0-flash

    <

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     supermarkets
    -0.53
    AccessorTable
    -0.47
     rain
    -0.45
     supermarket
    -0.43
    PerSecond
    -0.43
     ovunque
    -0.43
     Socialista
    -0.42
     araw
    -0.42
     <
    -0.42
     Infatti
    -0.42
    POSITIVE LOGITS
    numerusform
    0.83
    sizeCache
    0.80
    IsMutable
    0.78
    UserScript
    0.77
    windowFixed
    0.77
    protoc
    0.75
    CppMethod
    0.75
    matchCondition
    0.75
    complexType
    0.74
    DebuggerNonUser
    0.73
    Activations Density 5.805%

    No Known Activations