© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 12668
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols, equations, and related terminology

    oai_token-act-pair · gemini-2.0-flash

    ll

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    Hrsg
    -0.51
    rungsseite
    -0.47
     BoxFit
    -0.44
    led
    -0.44
     ExecuteAsync
    -0.43
     légales
    -0.43
    公
    -0.43
    рас
    -0.42
     bao
    -0.42
    出版年
    -0.42
    POSITIVE LOGITS
    IsContent
    0.72
    apunov
    0.67
    numerusform
    0.67
     Efq
    0.65
    uxxxx
    0.64
    حياته
    0.60
     AttributeSet
    0.59
    BibitemShut
    0.57
     himſelf
    0.57
     whofe
    0.55
    Activations Density 5.254%

    No Known Activations