© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 12332
    Prev
    Next
    INDEX
    Explanations

    the word "recognized" or "recognizes"

    oai_token-act-pair · gemini-2.0-flash

    recognize

    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
     recognize
    -1.13
     recognizes
    -1.08
    recognized
    -0.96
     recognizing
    -0.95
     recognition
    -0.95
     Recognizing
    -0.95
    recognition
    -0.94
     recognized
    -0.90
     Recognize
    -0.88
    recognize
    -0.87
    POSITIVE LOGITS
    EDEFAULT
    0.65
    (
    0.64
    "
    0.62
    OGND
    0.59
     nonatomic
    0.56
     Merritt
    0.56
     zákaz
    0.56
     PRACT
    0.55
     EClass
    0.55
     McCl
    0.54
    Activations Density 0.218%

    No Known Activations