© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 5979
    Prev
    Next
    INDEX
    Explanations

    C code syntax and assembly language instructions related to system calls

    oai_token-act-pair · gemini-2.0-flash

    Computer addresses / instructions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     lenker
    -0.73
    parsedMessage
    -0.55
     ErrIntOverflow
    -0.54
    FactoryBean
    -0.52
     admiten
    -0.49
     كومونز
    -0.46
     Surv
    -0.46
     JUDGMENT
    -0.46
    skraft
    -0.45
     audition
    -0.45
    POSITIVE LOGITS
     address
    0.63
    twimg
    0.60
     instruction
    0.59
     addresses
    0.57
    getAddress
    0.57
    Географи
    0.55
    instructions
    0.53
     Италијани
    0.53
     Address
    0.52
     getAddress
    0.52
    Activations Density 4.710%

    No Known Activations