© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9633
    Prev
    Next
    INDEX
    Explanations

    complex equations with exponential terms

    oai_token-act-pair · gemini-2.0-flash

    exp

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     mix
    -0.49
     Betracht
    -0.47
     mapas
    -0.47
    发表于
    -0.45
    DOCTYPE
    -0.44
    prefixer
    -0.43
     split
    -0.43
    Imm
    -0.42
     Carboniferous
    -0.41
    (":");
    -0.41
    POSITIVE LOGITS
    IntoConstraints
    0.94
    tagHelperRunner
    0.65
     Paglinawan
    0.62
     EconPapers
    0.59
     greateſt
    0.58
     ſeveral
    0.58
     offerts
    0.57
     Himo
    0.57
    KommentareTeilen
    0.57
     rechange
    0.57
    Activations Density 7.807%

    No Known Activations