© 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. 4924
    Prev
    Next
    INDEX
    Explanations

    words that would be used to issue a warning

    oai_token-act-pair · gemini-2.0-flash

    warning

    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
     autorytatywna
    -0.88
     nahilalakip
    -0.85
    createComponent
    -0.82
     незавершена
    -0.79
     '\\;'
    -0.74
    yntaxException
    -0.73
    ArgsConstructor
    -0.72
    MigrationBuilder
    -0.71
    AutoresizingMask
    -0.65
    urlpatterns
    -0.65
    POSITIVE LOGITS
     warning
    2.34
     Warning
    2.03
     warn
    1.98
     warnings
    1.93
     warned
    1.92
     WARNING
    1.86
    Warning
    1.84
    warning
    1.82
     caution
    1.81
     warns
    1.79
    Activations Density 1.213%

    No Known Activations