© 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
    2. Gemma-2-2B
    3. 12-GEMMASCOPE-TRANSCODER-16K
    4. 13269
    Prev
    Next
    INDEX
    Explanations

    adjectives describing quantities, often near the word "exactly" or "precisely"

    oai_token-act-pair · gemini-2.0-flash

    precisely

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    endpush
    -0.57
    multicolumn
    -0.47
    Using
    -0.46
    žio
    -0.46
    купить
    -0.45
     kindred
    -0.43
    using
    -0.42
    ˈ
    -0.42
    msgSender
    -0.42
    agaimana
    -0.41
    POSITIVE LOGITS
    enumii
    0.88
     المعيارى
    0.73
     muualla
    0.68
    ########.
    0.68
    sizeCache
    0.68
    WebElementEntity
    0.66
    enumi
    0.66
     Biôgrafia
    0.65
     CreateTagHelper
    0.65
    Дереккөздер
    0.64
    Activations Density 1.292%

    No Known Activations