© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 11672
    Prev
    Next
    INDEX
    Explanations

    HTML paragraph tags

    oai_token-act-pair · gemini-2.0-flash

    p

    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
    出版年
    -0.73
    DockStyle
    -0.71
    AccessorTable
    -0.69
    Hochspringen
    -0.68
    ammans
    -0.67
    RegistryLite
    -0.67
    HasAnnotation
    -0.66
    PyExc
    -0.66
     Normdatei
    -0.66
     autorytatywna
    -0.65
    POSITIVE LOGITS
    <bos>
    0.82
    elemField
    0.52
    )];
    0.48
    θεια
    0.47
     своим
    0.46
     geograf
    0.46
    sela
    0.46
    ниципа
    0.45
     figyel
    0.45
     c
    0.44
    Activations Density 0.130%

    No Known Activations