© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 2981
    Prev
    Next
    INDEX
    Explanations

    positive adjectives and verbs related to attracting and engaging people

    oai_token-act-pair · gemini-2.0-flash

    interesting content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     FormData
    -0.56
    ENDIAN
    -0.51
    discrete
    -0.51
    ribution
    -0.51
    AttributeSet
    -0.51
    amling
    -0.50
    requireNonNull
    -0.50
    tvguidetime
    -0.49
    etCode
    -0.49
    baka
    -0.49
    POSITIVE LOGITS
     appeal
    0.59
     entice
    0.57
    Attra
    0.56
     initComponents
    0.55
     appealing
    0.54
     attraction
    0.54
     للاسماء
    0.54
     attractive
    0.54
     captivated
    0.54
     بيها
    0.54
    Activations Density 0.844%

    No Known Activations