© 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
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 12514
    Prev
    Next
    INDEX
    Explanations

    words related to grief, loss, and memory, particularly in relation to identity and storytelling.

    oai_token-act-pair · gemini-2.0-flash

    uncommon or foreign references

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

    Writing and stories

    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
    setScene
    -0.39
    ap
    -0.38
    哥
    -0.35
     råd
    -0.33
     autor
    -0.33
     deputado
    -0.32
    able
    -0.32
    is
    -0.31
     udara
    -0.31
    var
    -0.31
    POSITIVE LOGITS
     Roskov
    0.96
     الرياضيه
    0.91
     referenties
    0.90
     autorytatywna
    0.90
    хьтан
    0.88
     ―――――
    0.87
    ArrowToggle
    0.85
     ſind
    0.84
    mybatisplus
    0.82
    PerformLayout
    0.82
    Activations Density 2.712%

    No Known Activations