© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4460
    Prev
    Next
    INDEX
    Explanations

    code snippets that include file operations like opening and copying, or mentions of I2C sensors and flight controllers

    oai_token-act-pair · gemini-2.0-flash

    terms related to navigation headers

    np_token-act-pair-logits · gpt-4o-mini

    Navigation and flight instruments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.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
     âme
    -0.60
    ristiana
    -0.60
     hiér
    -0.58
     pneumonia
    -0.57
    TintMode
    -0.56
     isolato
    -0.56
     marié
    -0.55
    dymyr
    -0.55
     réaliste
    -0.55
    شب
    -0.54
    POSITIVE LOGITS
     heading
    0.63
     Heading
    0.61
    ContextHolder
    0.57
     navigation
    0.57
    Heading
    0.54
    Portály
    0.54
     al
    0.53
     Navigation
    0.52
    EndGlobalSection
    0.52
    utives
    0.51
    Activations Density 2.947%

    No Known Activations