© 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. 2372
    Prev
    Next
    INDEX
    Explanations

    text that compares one thing as unlike or better than another

    oai_token-act-pair · gemini-2.0-flash

    comparison and differentiation

    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
     Theſe
    -0.47
     inalámb
    -0.42
    himura
    -0.40
     tambi
    -0.40
    ślę
    -0.40
     Anche
    -0.40
    Conclusie
    -0.40
    LayoutPanel
    -0.39
     düğün
    -0.39
    GIVEREF
    -0.39
    POSITIVE LOGITS
     nakalista
    0.82
     resourceCulture
    0.71
     those
    0.67
    WebVitals
    0.67
    IContainer
    0.64
     @"/
    0.64
     other
    0.63
    Geplaatst
    0.62
    tagext
    0.62
    IsContent
    0.61
    Activations Density 7.009%

    No Known Activations