© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 13465
    Prev
    Next
    INDEX
    Explanations

    code snippets, especially related to references, returning null, and stackoverflow

    oai_token-act-pair · gemini-2.0-flash

    ref

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    帖最后由
    -0.77
     photolibrary
    -0.76
    apatalk
    -0.76
    lloworld
    -0.75
     Wicidata
    -0.75
    ingtones
    -0.74
     AssemblyCulture
    -0.74
     '\\;'
    -0.73
    WebpackPlugin
    -0.73
     TextAlign
    -0.73
    POSITIVE LOGITS
     Brücke
    0.55
    old
    0.54
     genomen
    0.51
     aussehen
    0.51
    via
    0.50
    base
    0.50
     agora
    0.50
     pase
    0.50
     steg
    0.50
    EC
    0.50
    Activations Density 3.026%

    No Known Activations