© 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. 2387
    Prev
    Next
    INDEX
    Explanations

    computer-related terms and concepts along with financial jargon and vague relational words like "like" or "under"

    oai_token-act-pair · gemini-2.0-flash

    instructions or usage

    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
     uintptr
    -0.72
    abestanden
    -0.71
     zirc
    -0.66
     мәкал
    -0.65
     Tira
    -0.65
     parli
    -0.63
    mybatisplus
    -0.62
    /**
    -0.60
     CJK
    -0.59
     ſche
    -0.59
    POSITIVE LOGITS
    WithIOException
    0.63
    horesis
    0.50
     com
    0.49
     mode
    0.48
    NamedQueries
    0.47
     Ste
    0.47
    WithIdentifier
    0.46
     {"
    0.46
     po
    0.44
     Po
    0.43
    Activations Density 3.439%

    No Known Activations