© 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. 8280
    Prev
    Next
    INDEX
    Explanations

    Java code with json properties

    oai_token-act-pair · gemini-2.0-flash

    colons or parentheses

    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
     ExecuteAsync
    -0.59
    DoubleQuotes
    -0.57
     يتيمه
    -0.57
     Permalink
    -0.56
    ఔ
    -0.55
    Ashlee
    -0.53
    帖最后由
    -0.53
     Савезне
    -0.51
     CWE
    -0.49
     VIDEOTAPE
    -0.49
    POSITIVE LOGITS
    migrationBuilder
    0.54
    TagHelper
    0.45
     StatelessWidget
    0.44
    JpaRepository
    0.38
    AutoField
    0.38
    rrggbb
    0.37
    SpringBootTest
    0.36
    MemoryWarning
    0.36
     avsl
    0.36
    loem
    0.36
    Activations Density 0.556%

    No Known Activations