© 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. 10373
    Prev
    Next
    INDEX
    Explanations

    phrases that contain the articles "a" or "an" followed by an adjective

    oai_token-act-pair · gemini-2.0-flash

    a

    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
     viktigt
    -0.41
     fundamentales
    -0.39
     coscienza
    -0.39
     dimo
    -0.38
     bizony
    -0.38
     hígado
    -0.38
    ver
    -0.35
     creemos
    -0.35
     fossero
    -0.34
    </i>
    -0.34
    POSITIVE LOGITS
    RegressionTest
    0.93
     propOrder
    0.89
     Efq
    0.88
    ModelSerializer
    0.87
     Shakspeare
    0.86
     Alembic
    0.84
     HasFactory
    0.83
    XmlEnum
    0.81
     AssemblyProduct
    0.79
    </tfoot>
    0.79
    Activations Density 1.241%

    No Known Activations