© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13514
    Prev
    Next
    INDEX
    Explanations

    words related to human heart and physical adversaries

    oai_token-act-pair · gemini-2.0-flash

    terms related to artificial hearts

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

    the human heart

    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
    MemoryWarning
    -0.77
    expandindo
    -0.71
    Искәрмәләр
    -0.64
    utilisons
    -0.63
    EnableWeb
    -0.61
    RectangleBorder
    -0.61
    ManyToMany
    -0.60
    TintMode
    -0.60
    mybatisplus
    -0.58
     spesa
    -0.58
    POSITIVE LOGITS
     fallen
    0.54
     nature
    0.53
    atura
    0.49
    wußt
    0.47
    initComponents
    0.46
     natur
    0.45
     natura
    0.44
     עמ
    0.44
    fallen
    0.44
    artifactId
    0.44
    Activations Density 1.498%

    No Known Activations