© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 10255
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to technical or scientific topics across a variety of domains like computing, energy, biology, geography and marketing

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    <bos>
    -0.70
    ScopeManager
    -0.69
    djangoproject
    -0.65
    mergeFrom
    -0.65
     defaultstate
    -0.63
    WriteTagHelper
    -0.63
     تضيفلها
    -0.63
     Chwiliwch
    -0.62
    styleable
    -0.62
    ISupport
    -0.60
    POSITIVE LOGITS
    })$}
    0.54
    同じく
    0.51
    linik
    0.50
     yours
    0.49
    icle
    0.48
    otropy
    0.48
    ついで
    0.48
    ību
    0.47
     theirs
    0.47
    ว่า
    0.46
    Activations Density 5.112%

    No Known Activations