© 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. 4878
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions, especially formulas with Gamma functions and hypergeometric functions

    oai_token-act-pair · gemini-2.0-flash

    geometric

    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
    StoryboardSegue
    -0.75
    \{\\
    -0.56
    Gruß
    -0.55
     MonoBehaviour
    -0.55
    Espèce
    -0.54
    🏻
    -0.54
     rest
    -0.54
    :✨
    -0.53
     EconPapers
    -0.53
    tzmann
    -0.52
    POSITIVE LOGITS
    kloped
    0.51
    mtrl
    0.47
    SpringRunner
    0.47
     isInitialized
    0.45
    äden
    0.44
    GIVEREF
    0.44
     vej
    0.44
    ///</
    0.44
    HasAnnotation
    0.44
     legacies
    0.43
    Activations Density 2.854%

    No Known Activations