© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15805
    Prev
    Next
    INDEX
    Explanations

    places where the writer is acknowledging a differing viewpoint or stating uncertainty

    oai_token-act-pair · gemini-2.0-flash

    though

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     Aton
    -0.59
    ThroughAttribute
    -0.55
     Thur
    -0.55
    Ử
    -0.50
     shawl
    -0.50
     Mollus
    -0.49
    complexType
    -0.49
    Tembelea
    -0.47
     Schleswig
    -0.46
    <caption>
    -0.45
    POSITIVE LOGITS
     they
    0.69
     we
    0.61
     there
    0.60
     it
    0.59
     nothing
    0.58
    cely
    0.54
    '],$
    0.54
     Partagez
    0.54
    cyklopedia
    0.54
     cathédrale
    0.53
    Activations Density 5.779%

    No Known Activations