© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 11046
    Prev
    Next
    INDEX
    Explanations

    words that are frequently found in online posts

    oai_token-act-pair · gemini-2.0-flash

    social media/issues

    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
    <bos>
    -0.73
    }`).
    -0.63
    //</
    -0.60
     препратки
    -0.56
    migrationBuilder
    -0.52
    %</
    -0.49
     ویکی‌آمباردا
    -0.49
    "]').
    -0.49
     ""}
    -0.48
    ]='\
    -0.47
    POSITIVE LOGITS
    AnimationsModule
    0.66
    TProtocol
    0.65
    ConverterFactory
    0.64
    richTextPanel
    0.59
    ResponseWriter
    0.58
     kasarigan
    0.57
     '\\;'
    0.56
    NewUrlParser
    0.56
    Παραπομπές
    0.50
    HideFlags
    0.50
    Activations Density 1.470%

    No Known Activations