© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 13443
    Prev
    Next
    INDEX
    Explanations

    numbers, numerical ranges, and related terms in the context of what appears to be some sort of research data

    oai_token-act-pair · gemini-2.0-flash

    genetic data

    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
     AssemblyCulture
    -0.52
    WarningLevel
    -0.50
     بيها
    -0.50
    ":[{
    -0.49
    StreetMap
    -0.48
    fiez
    -0.47
    MigrationBuilder
    -0.47
    ercizio
    -0.46
    <bos>
    -0.46
    smithy
    -0.45
    POSITIVE LOGITS
    writeFieldEnd
    0.71
    曖昧さ回避
    0.58
     appar
    0.56
    /**
    0.56
    ']));
    0.55
    */;
    0.54
     initWithFrame
    0.53
    存于互联网档案馆
    0.51
    Biografía
    0.51
    )))));
    0.51
    Activations Density 1.672%

    No Known Activations