© 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. 11424
    Prev
    Next
    INDEX
    Explanations

    location names, numbers and names of people in the document, especially when adjacent to each other.

    oai_token-act-pair · gemini-2.0-flash

    stered

    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
     Audiodateien
    -0.84
     оригіналу
    -0.77
    )++;
    -0.70
    forChild
    -0.70
    isissez
    -0.69
    tableFuture
    -0.66
    /*
    -0.65
    ūrė
    -0.65
     numberOfRows
    -0.64
     tslint
    -0.63
    POSITIVE LOGITS
    出版年
    0.46
    aturen
    0.39
    Legenda
    0.39
    setOn
    0.38
     pel
    0.38
    gone
    0.37
     ModelExpression
    0.37
    期刊论文
    0.36
    Sucesor
    0.36
    kan
    0.35
    Activations Density 20.800%

    No Known Activations