© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 4808
    Prev
    Next
    INDEX
    Explanations

    words and phrases that describe cause and effect.

    oai_token-act-pair · gemini-2.0-flash

    scientific problem solving

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    컴
    -0.52
    ©
    -0.46
     multiple
    -0.42
    @
    -0.41
    wit
    -0.41
     ©
    -0.37
    сунок
    -0.37
    Jeez
    -0.37
    multiple
    -0.37
     stretch
    -0.37
    POSITIVE LOGITS
    ThroughAttribute
    0.78
    PreExecute
    0.77
     propOrder
    0.72
    קישורים
    0.71
    RegistryLite
    0.65
     mergeFrom
    0.65
    WriteTagHelper
    0.64
     Roskov
    0.61
     hereof
    0.61
    AddTagHelper
    0.59
    Activations Density 3.355%

    No Known Activations