© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10560
    Prev
    Next
    INDEX
    Explanations

    technical jargon and code snippets

    oai_token-act-pair · gemini-2.0-flash

    code identifiers

    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
     CreateTagHelper
    -1.11
     незавершена
    -0.94
     estekak
    -0.89
     AssemblyProduct
    -0.85
     Normdatei
    -0.79
    ArgsConstructor
    -0.77
     للمعارف
    -0.75
     disambiguazione
    -0.75
    tangentMode
    -0.75
    SharedCtor
    -0.75
    POSITIVE LOGITS
     bolas
    0.50
     Nass
    0.50
    modal
    0.46
     lands
    0.43
    astă
    0.43
     previsão
    0.42
    assador
    0.42
    ERVE
    0.42
    inol
    0.41
     Geh
    0.41
    Activations Density 0.597%

    No Known Activations