© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 9182
    Prev
    Next
    INDEX
    Explanations

    words and phrases from legal or academic documents and studies.

    oai_token-act-pair · gemini-2.0-flash

    studies and assessments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     resourceCulture
    -0.72
    tagHelperRunner
    -0.70
     שוליים
    -0.63
     الرياضيه
    -0.62
    exitRule
    -0.60
     Meksiku
    -0.53
    ByVersion
    -0.53
     surla
    -0.52
    таратура
    -0.51
     تضيفلها
    -0.51
    POSITIVE LOGITS
     study
    1.30
     studies
    1.17
     Study
    1.14
     feasibility
    1.10
     analysis
    1.10
     STUDY
    1.09
    Study
    1.06
    study
    1.05
     assessment
    1.00
     assessments
    0.99
    Activations Density 2.702%

    No Known Activations