© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8224
    Prev
    Next
    INDEX
    Explanations

    sentences that use the word "to"

    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_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    ########.
    -0.77
     صوتيه
    -0.62
     تضيفلها
    -0.60
    memoized
    -0.59
    étit
    -0.59
     AssemblyProduct
    -0.59
    lwjgl
    -0.57
    TintMode
    -0.55
    UnsafeEnabled
    -0.54
     елның
    -0.54
    POSITIVE LOGITS
    brainly
    0.47
    Hentet
    0.46
    mayo
    0.45
    co
    0.45
    SequentialGroup
    0.45
    cookieParser
    0.44
     समीक्षाएं
    0.42
    ớt
    0.42
     sc
    0.42
    ниципа
    0.42
    Activations Density 2.606%

    No Known Activations