© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 323
    Prev
    Next
    INDEX
    Explanations

    code snippets, especially file paths and web addresses

    oai_token-act-pair · gemini-2.0-flash

    /

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    νή
    -0.50
    shadowOffset
    -0.50
     CreateTagHelper
    -0.48
    TagHelper
    -0.48
    FieldOffset
    -0.47
    المكان
    -0.46
     pinulongan
    -0.45
    endphp
    -0.45
     chcete
    -0.45
    InputLabel
    -0.44
    POSITIVE LOGITS
    expandindo
    0.88
    ApiModel
    0.70
    发表于
    0.65
    InstrumentedTest
    0.65
    AndroidJUnit
    0.64
     <>",
    0.59
    dagog
    0.56
    #+#
    0.56
    Hentet
    0.56
    SpringBootTest
    0.55
    Activations Density 0.973%

    No Known Activations