© 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. 14086
    Prev
    Next
    INDEX
    Explanations

    a mixture of possible categories, including internet terms, abbreviated terminology, non-English languages and terms related to race

    oai_token-act-pair · gemini-2.0-flash

    equinox

    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
    testdata
    -0.63
     cons
    -0.63
    AddTagHelper
    -0.62
     بيها
    -0.59
     pro
    -0.56
    orija
    -0.55
    Portale
    -0.54
    uminense
    -0.54
    خصة
    -0.52
    டம்
    -0.52
    POSITIVE LOGITS
     ſche
    0.91
     Diſ
    0.84
    es
    0.82
     Eſ
    0.82
     itſelf
    0.82
     neceff
    0.82
     iſt
    0.78
     Reſ
    0.77
     Inſ
    0.77
     pngtree
    0.77
    Activations Density 1.367%

    No Known Activations