© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 10855
    Prev
    Next
    INDEX
    Explanations

    words or short phrases related to scientific research being conducted or methods for accomplishing it

    oai_token-act-pair · gemini-2.0-flash

    proximity

    np_max-act · 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
    writeField
    -0.87
    writeFieldEnd
    -0.80
     للمعارف
    -0.77
    contentLoaded
    -0.75
    protoimpl
    -0.74
    NOPQRST
    -0.71
    RUnlock
    -0.69
     suivantes
    -0.68
    AsUp
    -0.68
    DropTable
    -0.67
    POSITIVE LOGITS
     roll
    0.49
     rolls
    0.48
     modern
    0.47
    fml
    0.45
    sy
    0.45
     two
    0.44
     double
    0.44
    cipar
    0.43
     the
    0.42
    $^\
    0.42
    Activations Density 3.338%

    No Known Activations