© 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. 1071
    Prev
    Next
    INDEX
    Explanations

    sentences with "I always"

    oai_token-act-pair · gemini-2.0-flash

    always

    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
    IntoConstraints
    -0.69
    ManagedBean
    -0.62
     payé
    -0.61
    UnitTesting
    -0.61
     auroit
    -0.59
    RectangleBorder
    -0.59
     verrez
    -0.55
     quæ
    -0.55
     وتسجيلات
    -0.55
     médec
    -0.54
    POSITIVE LOGITS
     EconPapers
    0.48
     be
    0.47
    yntaxException
    0.47
     try
    0.43
     sih
    0.42
     incumbent
    0.41
    gestone
    0.41
    فتر
    0.40
     ape
    0.40
    zystać
    0.40
    Activations Density 8.516%

    No Known Activations