© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 12054
    Prev
    Next
    INDEX
    Explanations

    the word "window" or related words

    oai_token-act-pair · gemini-2.0-flash

    window

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     myſelf
    -0.96
    ſelves
    -0.95
    ſelf
    -0.94
     ſeveral
    -0.93
     raiſ
    -0.93
     Jefus
    -0.93
     Efq
    -0.91
     purpoſe
    -0.91
     poffible
    -0.90
     themſelves
    -0.83
    POSITIVE LOGITS
    ing
    0.72
    ING
    0.61
    发表于
    0.55
    ed
    0.50
    RRect
    0.46
    gameserver
    0.44
    minecraftforge
    0.43
     trình
    0.41
    ning
    0.41
    ába
    0.40
    Activations Density 4.459%

    No Known Activations