© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 7583
    Prev
    Next
    INDEX
    Explanations

    words, phrases and sentence fragments commonly used in legal opinions

    oai_token-act-pair · gemini-2.0-flash

    there

    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
    
    -0.90
     متعلقه
    -0.90
    цездатний
    -0.89
    ThroughAttribute
    -0.88
    writeFieldEnd
    -0.88
     незавершена
    -0.86
    KommentareTeilen
    -0.86
    Atsauces
    -0.85
     contextLoads
    -0.84
    Hochspringen
    -0.84
    POSITIVE LOGITS
     we
    0.56
     is
    0.53
     
    0.50
     he
    0.49
     to
    0.49
     M
    0.47
    ?
    0.46
      
    0.45
     http
    0.44
     I
    0.42
    Activations Density 0.593%

    No Known Activations