© 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. 3032
    Prev
    Next
    INDEX
    Explanations

    the word "which" and nearby words.

    oai_token-act-pair · gemini-2.0-flash

    which

    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
    uxxxx
    -0.75
    <bos>
    -0.69
     beginnetje
    -0.67
    WithIOException
    -0.62
     Paglinawan
    -0.62
     referenties
    -0.58
     EconPapers
    -0.57
    ')}}
    -0.55
    principalTable
    -0.54
    MessageOf
    -0.54
    POSITIVE LOGITS
     sumpay
    0.52
    manjaro
    0.49
    стка
    0.49
    ंज
    0.48
    hringer
    0.48
     entrepreneur
    0.48
    Yung
    0.47
    ruvate
    0.45
     snippetHide
    0.45
    ParallelGroup
    0.45
    Activations Density 3.485%

    No Known Activations