© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 15665
    Prev
    Next
    INDEX
    Explanations

    text inside quotation marks

    oai_token-act-pair · gemini-2.0-flash

    quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    SharedCtor
    -0.92
     estekak
    -0.87
    MemoryWarning
    -0.79
     EconPapers
    -0.78
    PerformLayout
    -0.78
    IUrlHelper
    -0.77
     متعلقه
    -0.76
     OFDb
    -0.76
    RectangleBorder
    -0.74
    __;
    -0.73
    POSITIVE LOGITS
    erapeu
    0.83
    <bos>
    0.76
    '
    0.55
    ↵↵
    0.54
    abyrinth
    0.53
     Shakspeare
    0.50
     Gouvernement
    0.49
     dinilai
    0.49
     præ
    0.48
     Queste
    0.48
    Activations Density 0.572%

    No Known Activations