© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 12394
    Prev
    Next
    INDEX
    Explanations

    HTML tags or attributes

    oai_token-act-pair · gemini-2.0-flash

    div

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     AND
    -0.54
     And
    -0.48
    na
    -0.46
    And
    -0.45
    i
    -0.44
     /
    -0.44
    q
    -0.43
    /
    -0.43
    原始内容
    -0.42
    gren
    -0.41
    POSITIVE LOGITS
     snippetHide
    0.91
     مشين
    0.88
     Efq
    0.88
     يتيمه
    0.88
     Roskov
    0.85
    __':
    0.84
    )))));
    0.82
     NSCoder
    0.82
     initComponents
    0.79
    ArgumentParser
    0.77
    Activations Density 0.984%

    No Known Activations