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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10533
    Prev
    Next
    INDEX
    Explanations

    past-tense forms of the verb "to be" in contexts of awards and recognition

    oai_token-act-pair · gemini-2.0-flash

    was/be forms

    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
    PDOException
    -0.60
    popd
    -0.57
     propOrder
    -0.56
    astify
    -0.56
     Kashi
    -0.54
    zarchiwizowane
    -0.53
    impianto
    -0.53
    attuale
    -0.53
    Artik
    -0.52
     Kulit
    -0.52
    POSITIVE LOGITS
     للاسماء
    0.77
     ModelExpression
    0.56
     Normdatei
    0.56
     وتسجيلات
    0.54
    AtIndexPath
    0.52
     bén
    0.50
    UrlResolution
    0.49
    abetes
    0.48
     approved
    0.47
    grà
    0.47
    Activations Density 1.316%

    No Known Activations