© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12796
    Prev
    Next
    INDEX
    Explanations

    instances of "want to"

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     المعيارى
    -0.65
    erializer
    -0.65
    BASEPATH
    -0.64
     Landsat
    -0.61
    LEncoder
    -0.57
     насељу
    -0.55
     allAfrica
    -0.54
    ⋙
    -0.54
     Vex
    -0.54
     NSCoder
    -0.54
    POSITIVE LOGITS
     bör
    0.53
    iconque
    0.49
     costruzione
    0.48
    æld
    0.48
    ']))
    0.48
     touristes
    0.48
     fonctionner
    0.48
     flesta
    0.48
     sanitarios
    0.47
    visning
    0.47
    Activations Density 1.028%

    No Known Activations