© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11240
    Prev
    Next
    INDEX
    Explanations

    modal verbs expressing possibility or obligation

    oai_token-act-pair · gemini-2.0-flash

    should or would

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     is
    -0.91
     has
    -0.72
    :✨
    -0.65
     does
    -0.62
    Portály
    -0.61
     ProtoMessage
    -0.60
     مشين
    -0.60
     testifies
    -0.59
     was
    -0.59
     betreft
    -0.58
    POSITIVE LOGITS
    piac
    0.58
    RRect
    0.57
    AnimationFrame
    0.57
     agree
    0.55
    sequelize
    0.54
    amqp
    0.52
     accompli
    0.52
     try
    0.52
    isition
    0.50
    CppCodeGen
    0.50
    Activations Density 0.506%

    No Known Activations