© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12354
    Prev
    Next
    INDEX
    Explanations

    words related to death, burial, and memorials, but with some exceptions

    oai_token-act-pair · gemini-2.0-flash

    death

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    fjspx
    -0.80
     resourceCulture
    -0.79
     دریافت‌شده
    -0.74
     propOrder
    -0.71
    expandindo
    -0.70
    +#+
    -0.69
     Winaray
    -0.66
     Paglinawan
    -0.65
    ьаж
    -0.65
    DrawerToggle
    -0.65
    POSITIVE LOGITS
     acaso
    0.46
     مواليد
    0.45
     ga
    0.44
    tableLayoutPanel
    0.44
    recorded
    0.43
     Voraus
    0.42
     gag
    0.42
    geld
    0.42
     suivants
    0.42
    влено
    0.42
    Activations Density 1.131%

    No Known Activations