© 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. 4198
    Prev
    Next
    INDEX
    Explanations

    someone trying something

    oai_token-act-pair · 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
     try
    -0.85
     Try
    -0.84
    try
    -0.81
    Try
    -0.74
     tried
    -0.68
     tries
    -0.63
     Tried
    -0.60
     TRY
    -0.59
     trying
    -0.57
     attempt
    -0.56
    POSITIVE LOGITS
     Савезне
    0.96
    Personensuche
    0.91
    ConstraintMaker
    0.88
    ."</
    0.86
    ")));
    0.84
    EndGlobalSection
    0.82
    oredCriteria
    0.80
    )");
    0.78
    ModelBuilder
    0.78
     Theſe
    0.76
    Activations Density 4.498%

    No Known Activations