© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14702
    Prev
    Next
    INDEX
    Explanations

    references related to someone being dead, dying, or burial

    oai_token-act-pair · gemini-2.0-flash

    die

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    +#+#
    -0.73
    adaptiveStyles
    -0.71
     فريبيس
    -0.68
    TagMode
    -0.68
    writeHead
    -0.62
     homotopy
    -0.61
     kaynağından
    -0.61
     المعيارى
    -0.59
    mybatisplus
    -0.57
     fusca
    -0.55
    POSITIVE LOGITS
     of
    0.50
     in
    0.48
    ")));
    0.46
     силы
    0.45
    homonymie
    0.44
    *)((
    0.44
     based
    0.44
    {}{}
    0.43
     dag
    0.43
    port
    0.43
    Activations Density 4.783%

    No Known Activations