© 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. 8433
    Prev
    Next
    INDEX
    Explanations

    complex author name patterns in academic citations

    oai_token-act-pair · gemini-2.0-flash

    technical terminology and specialized vocabulary

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

    Research or scientific papers

    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
    for
    -0.59
    .
    -0.57
     for
    -0.54
    ...
    -0.51
    ;
    -0.50
    …
    -0.50
    to
    -0.49
     their
    -0.49
    ens
    -0.49
     this
    -0.49
    POSITIVE LOGITS
     مرئيه
    0.90
     мәкал
    0.68
    RectangleBorder
    0.66
    XmlAccessType
    0.65
    Jeografia
    0.64
    PhysRevD
    0.64
     &___
    0.63
     localObject
    0.63
    mybatisplus
    0.63
     Evaluation
    0.62
    Activations Density 3.063%

    No Known Activations