© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 1162
    Prev
    Next
    INDEX
    Explanations

    code-related terms, including HTML tags, variables, and Javascript functions

    oai_token-act-pair · gemini-2.0-flash

    quiz

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     ddelweddau
    -0.57
     otomatig
    -0.49
    ValueStyle
    -0.48
     MediatR
    -0.48
    enderror
    -0.48
    Tikang
    -0.47
    UnknownFields
    -0.46
    MessageState
    -0.45
    writeFieldEnd
    -0.45
    Autoritní
    -0.44
    POSITIVE LOGITS
    LikeLike
    0.63
    Przypisy
    0.61
     Tuch
    0.60
    ক্ষ
    0.57
    geries
    0.57
    LogFactory
    0.56
    ైన
    0.56
     Aufenthal
    0.56
    hý
    0.55
     bertahan
    0.55
    Activations Density 28.620%

    No Known Activations