© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13102
    Prev
    Next
    INDEX
    Explanations

    instances of using "want" and "to" together in phrases

    oai_token-act-pair · gemini-2.0-flash

    to

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     betweenstory
    -0.70
    astéroïdes
    -0.60
     Савезне
    -0.58
    richTextPanel
    -0.56
    FormTagHelper
    -0.55
    picasso
    -0.54
    kháu
    -0.52
     okuyayım
    -0.52
     đâu
    -0.52
     cherchés
    -0.52
    POSITIVE LOGITS
    weisen
    0.46
     subli
    0.46
    رشف
    0.46
     trest
    0.45
    MotionEvent
    0.44
     brush
    0.43
     sublimation
    0.43
     brilh
    0.43
    fil
    0.43
    ]--;
    0.43
    Activations Density 0.498%

    No Known Activations