© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12529
    Prev
    Next
    INDEX
    Explanations

    code snippets including the word "model" and references to Keras

    oai_token-act-pair · gemini-2.0-flash

    technical or programming terminology

    np_token-act-pair-logits · gpt-4o-mini

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    featureID
    -0.82
    ंदीखरीदारी
    -0.74
    TagMode
    -0.64
    styleType
    -0.64
    EndInit
    -0.63
    Autoritní
    -0.63
     AssemblyTitle
    -0.62
    BeginInit
    -0.62
     AssemblyVersion
    -0.61
    Atoi
    -0.61
    POSITIVE LOGITS
    oderma
    0.52
    Initializable
    0.49
    site
    0.45
    ofo
    0.45
     funghi
    0.44
    ibilité
    0.42
    wpi
    0.41
    RATION
    0.41
    setContentView
    0.41
    漫
    0.40
    Activations Density 0.224%

    No Known Activations