© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11708
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to a variety of fields, including hunting, religion, recreation, medicine, genetics, and racing

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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>
    -0.86
     thereof
    -0.52
     format
    -0.52
    boten
    -0.52
    format
    -0.51
     digress
    -0.49
    Format
    -0.48
    ierende
    -0.48
     thereto
    -0.47
    sver
    -0.47
    POSITIVE LOGITS
    PyExc
    0.70
    MigrationBuilder
    0.69
     TestBed
    0.68
    ukone
    0.63
     发表于
    0.63
     ModelExpression
    0.61
     Roskov
    0.61
    icitis
    0.61
    tagHelperRunner
    0.60
     Voiture
    0.60
    Activations Density 3.084%

    No Known Activations