© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2067
    Prev
    Next
    INDEX
    Explanations

    a variety of markers indicating distinct text sections such as salutations, dates and pronouns referring to the speaker.

    oai_token-act-pair · gemini-2.0-flash

    proper nouns or names

    np_token-act-pair-logits · gpt-4o-mini

    Proper nouns in diverse text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     insuffisamment
    -0.47
    addComponent
    -0.47
    出版年
    -0.44
    addTab
    -0.43
    참고
    -0.43
    Ligações
    -0.42
    BorderLayout
    -0.42
     nhật
    -0.42
     consiguiente
    -0.42
    шеб
    -0.42
    POSITIVE LOGITS
    :✨
    0.66
    colgroup
    0.62
    openzeppelin
    0.60
     Mathew
    0.59
     Nathan
    0.57
     Samuel
    0.57
     Jacob
    0.55
    клопе
    0.54
    AxisAlignment
    0.54
     Nicholas
    0.54
    Activations Density 4.867%

    No Known Activations