© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 226
    Prev
    Next
    INDEX
    Explanations

    various snippets of code, physical descriptions and legal jargon

    oai_token-act-pair · gemini-2.0-flash

    describing objects and code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     Zusch
    -0.43
     Massen
    -0.42
     growth
    -0.42
    gouv
    -0.42
     büyü
    -0.41
     Maße
    -0.40
    Enllaços
    -0.40
    GYPT
    -0.39
     <<<<<<<<<<<<<<
    -0.39
     GROWTH
    -0.39
    POSITIVE LOGITS
     FontWeight
    0.81
    ביוגרפיה
    0.77
     onCancelled
    0.73
    ftagPool
    0.69
    tagext
    0.68
    borderSide
    0.67
    WebServlet
    0.66
    IsContent
    0.64
    发表于
    0.62
    Scénario
    0.60
    Activations Density 2.665%

    No Known Activations