© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6434
    Prev
    Next
    INDEX
    Explanations

    words related to Hinduism, especially names and festivals

    oai_token-act-pair · gemini-2.0-flash

    programming terms

    np_token-act-pair-logits · gpt-4o-mini
    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
     secoli
    -0.54
    AutoScaleMode
    -0.53
    nodoc
    -0.52
     siglos
    -0.50
     iprot
    -0.49
     împ
    -0.47
    moving
    -0.47
     initComponents
    -0.47
     سوی
    -0.47
    ➌
    -0.47
    POSITIVE LOGITS
    RenderAtEndOf
    0.84
    WithMany
    0.68
     groupBox
    0.60
    InputBorder
    0.58
    sha
    0.56
    DatabaseError
    0.54
    makeConstraints
    0.54
    什
    0.54
    orial
    0.52
     المعيارى
    0.52
    Activations Density 0.154%

    No Known Activations