© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 11658
    Prev
    Next
    INDEX
    Explanations

    code snippets, chemical formulas, or mathematical equations

    oai_token-act-pair · gemini-2.0-flash

    programming and references

    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
     "..\..\
    -0.65
    createClass
    -0.65
    WriteLiteral
    -0.64
    resseur
    -0.62
     CYTHON
    -0.60
     propOrder
    -0.60
    Tembelea
    -0.60
     szok
    -0.59
    ++];
    -0.59
    :]:
    -0.59
    POSITIVE LOGITS
     AssemblyCulture
    0.57
    <bos>
    0.50
    AccessorTable
    0.45
    MigrationBuilder
    0.43
    TagMode
    0.42
    0.42
    iastes
    0.41
    【
    0.40
    atrici
    0.40
    VersionUID
    0.39
    Activations Density 5.709%

    No Known Activations