© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8638
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to shellfish, snails, and fossils

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     shell
    -2.06
     Shell
    -1.94
    shell
    -1.91
    Shell
    -1.88
     shells
    -1.80
     SHELL
    -1.77
     Shells
    -1.69
    SHELL
    -1.56
    shells
    -1.49
    hells
    -1.34
    POSITIVE LOGITS
    וויק
    0.59
     المعيارى
    0.58
    setViewportView
    0.57
     épais
    0.52
    SpringRunner
    0.50
    Clik
    0.49
     مشين
    0.49
    CppMethod
    0.49
    ogonal
    0.49
     vastaan
    0.48
    Activations Density 1.410%

    No Known Activations