© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 15194
    Prev
    Next
    INDEX
    Explanations

    words that are part of, or close to, standard boilerplate, either in scientific papers or news articles.

    oai_token-act-pair · gemini-2.0-flash

    PG

    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
     الحره
    -0.85
    LookAnd
    -0.79
     ویکی‌پدیای
    -0.72
    ########.
    -0.71
     cherchés
    -0.68
    Diwedd
    -0.67
     فريبيس
    -0.66
     كومونز
    -0.66
    titleMargin
    -0.65
    bewerken
    -0.63
    POSITIVE LOGITS
    openConnection
    0.44
     altrimenti
    0.44
    ニーカー
    0.41
    دن
    0.41
     verba
    0.41
     vna
    0.41
     tratta
    0.38
    見えない
    0.37
    Initializable
    0.36
    JAKARTA
    0.36
    Activations Density 2.223%

    No Known Activations