© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 8268
    Prev
    Next
    INDEX
    Explanations

    technical jargon, locations, and measurements

    oai_token-act-pair · gemini-2.0-flash

    data extraction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    âtel
    -0.48
     发表于
    -0.46
    }}=$
    -0.45
    円
    -0.43
     dehors
    -0.42
     sed
    -0.42
    TagMode
    -0.41
    SourceChecksum
    -0.40
    رو
    -0.40
     OBITUARY
    -0.40
    POSITIVE LOGITS
    BeginContext
    0.64
    ########.
    0.63
     AssemblyCulture
    0.61
    Hentet
    0.59
    IonicModule
    0.59
     وتسجيلات
    0.57
    MigrationBuilder
    0.57
    Попис
    0.56
    bbene
    0.55
    новниш
    0.53
    Activations Density 1.334%

    No Known Activations