© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 5936
    Prev
    Next
    INDEX
    Explanations

    This neuron seems to be very good at finding a large number of keywords related to computer code, bicycle parts, and a particular foreign language

    oai_token-act-pair · gemini-2.0-flash

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    DockStyle
    -0.91
    RectangleBorder
    -0.90
    IsContent
    -0.80
    migrationBuilder
    -0.72
     GenerationType
    -0.71
    TemporalType
    -0.68
    ContentAsync
    -0.65
    PhysRev
    -0.63
    anthene
    -0.63
    "?>
    -0.63
    POSITIVE LOGITS
     linking
    0.43
    rue
    0.42
    tadır
    0.42
    횟
    0.41
    XDECREF
    0.40
    次
    0.40
    FAILURE
    0.38
     relevante
    0.38
    classpath
    0.38
    csolódó
    0.37
    Activations Density 14.927%

    No Known Activations