© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 4712
    Prev
    Next
    INDEX
    Explanations

    multiple different concepts making it difficult to determine one sentence to describe the neuron's purpose

    oai_token-act-pair · gemini-2.0-flash

    long time

    np_max-act-logits · gemini-2.0-flash

    long (duration)

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    ViewFeatures
    -0.73
     pinulongan
    -0.68
    HtmlAttribute
    -0.61
    antMatchers
    -0.56
    posedge
    -0.54
     оригіналу
    -0.53
    ArgsConstructor
    -0.51
    migrationBuilder
    -0.51
    EndContext
    -0.51
    ="../../
    -0.50
    POSITIVE LOGITS
     long
    1.35
    long
    1.15
     LONG
    1.08
    Long
    0.99
     Long
    0.95
     lâu
    0.95
     давно
    0.94
    LONG
    0.89
     years
    0.87
     longtemps
    0.87
    Activations Density 2.055%

    No Known Activations