© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11520
    Prev
    Next
    INDEX
    Explanations

    hexadecimal characters

    oai_token-act-pair · gemini-2.0-flash

    code-related language constructs

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

    Code snippets

    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
    Filmografie
    -0.65
    Fazit
    -0.62
    numerusform
    -0.62
     leksikon
    -0.60
    تقاوى
    -0.60
     createState
    -0.59
    DockStyle
    -0.58
    /*---
    -0.57
     تضيفلها
    -0.55
    #
    -0.55
    POSITIVE LOGITS
    Labels
    0.51
     continúas
    0.50
     parlato
    0.45
     Convey
    0.44
    áló
    0.43
    ποίη
    0.43
     لاس
    0.43
     VOOR
    0.42
     FormsModule
    0.42
    yscy
    0.42
    Activations Density 0.417%

    No Known Activations