© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14414
    Prev
    Next
    INDEX
    Explanations

    references to individual distinct items or categories and comparing them using words like 'each', 'different', and numerals.

    oai_token-act-pair · gemini-2.0-flash

    each

    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
    ViewImports
    -0.51
     <>",
    -0.51
    IsContent
    -0.51
    !*\
    -0.47
    ExecuteReader
    -0.47
    IndentedString
    -0.46
     estimés
    -0.44
     disambiguazione
    -0.44
    MLLoader
    -0.43
    entown
    -0.43
    POSITIVE LOGITS
     MainAxisSize
    0.59
    RUnlock
    0.57
     تكبرها
    0.57
    endpush
    0.56
    ACIONAL
    0.53
     setas
    0.53
     esternos
    0.52
    maß
    0.52
    Embeddable
    0.52
    VersionUID
    0.52
    Activations Density 18.372%

    No Known Activations