© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15551
    Prev
    Next
    INDEX
    Explanations

    code-related tokens, especially those occurring frequently within loops, data type declarations, conditional statements, or related to GUI element arrangements or temperature or padding properties

    oai_token-act-pair · gemini-2.0-flash

    say "= word"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    <unused61>
    -0.54
    </strong>
    -0.53
    ("
    -0.52
    <unused63>
    -0.51
    <unused62>
    -0.51
     signore
    -0.50
    <unused60>
    -0.49
    ('
    -0.49
    (
    -0.48
    ↵
    -0.47
    POSITIVE LOGITS
    AddTagHelper
    1.13
     <=",
    1.11
    DockStyle
    1.00
     BoxFit
    0.91
    parsedMessage
    0.91
    таратура
    0.90
    MigrationBuilder
    0.89
    RenderAtEndOf
    0.89
    extAlignment
    0.88
    basicConfig
    0.87
    Activations Density 1.643%

    No Known Activations