© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 5030
    Prev
    Next
    INDEX
    Explanations

    references to courts, judges, lawyers and other legal terms.

    oai_token-act-pair · gemini-2.0-flash

    Names and political titles

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
    PerformLayout
    -0.64
    ThroughAttribute
    -0.58
    ioutil
    -0.54
    ⓘ
    -0.49
    Tracce
    -0.48
     DMG
    -0.47
     surla
    -0.46
    isNotBlank
    -0.46
     >::
    -0.45
    rió
    -0.44
    POSITIVE LOGITS
    :✨
    0.76
    Personensuche
    0.68
    NameInMap
    0.66
    IndentedString
    0.63
    bestos
    0.61
     мәкал
    0.60
     protoimpl
    0.60
    jspx
    0.58
    CppMethod
    0.57
    agisse
    0.57
    Activations Density 1.284%

    No Known Activations