© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3296
    Prev
    Next
    INDEX
    Explanations

    a mixture of math, finance, and computer code.

    oai_token-act-pair · gemini-2.0-flash

    problem

    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
    rawDesc
    -0.78
    StructEnd
    -0.66
    Remarque
    -0.63
    IsContent
    -0.60
    Applies
    -0.60
    vogel
    -0.60
    InSection
    -0.59
    OpenHelper
    -0.59
    Cześć
    -0.59
    Witam
    -0.59
    POSITIVE LOGITS
    
    0.54
    parsedMessage
    0.42
    KommentareTeilen
    0.42
    esine
    0.42
    слова
    0.41
     vasca
    0.41
    QMetaType
    0.41
     verke
    0.40
    mi
    0.39
     iprot
    0.38
    Activations Density 3.225%

    No Known Activations