© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5703
    Prev
    Next
    INDEX
    Explanations

    instances of the abbreviation "rel" as it appears in legal citations

    oai_token-act-pair · gemini-2.0-flash

    rel

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    KommentareTeilen
    -0.87
     Pues
    -0.81
     adaptés
    -0.77
     auroit
    -0.77
     sanitaires
    -0.77
     étoit
    -0.77
     auffi
    -0.75
     Inhabitants
    -0.75
     enfans
    -0.75
     noires
    -0.75
    POSITIVE LOGITS
     a
    0.73
    Ligações
    0.65
     me
    0.65
    duled
    0.63
    hematical
    0.60
     “
    0.60
     an
    0.60
    drawal
    0.60
    iric
    0.56
     con
    0.56
    Activations Density 0.812%

    No Known Activations