© 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. 14234
    Prev
    Next
    INDEX
    Explanations

    legal citations, terms, and names and some related coding syntax

    oai_token-act-pair · gemini-2.0-flash

    at

    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
     ostavi
    -0.88
     EconPapers
    -0.79
    Portale
    -0.73
     nakalista
    -0.73
     CreateTagHelper
    -0.70
     >=",
    -0.68
    IUrlHelper
    -0.66
    webElementXpaths
    -0.65
    enderror
    -0.65
    WriteTagHelper
    -0.65
    POSITIVE LOGITS
    peque
    0.47
     purported
    0.41
    ibição
    0.41
    nein
    0.40
    mulo
    0.40
    progressDialog
    0.40
     Schie
    0.39
    IONS
    0.39
     potential
    0.39
    Vtbl
    0.39
    Activations Density 8.635%

    No Known Activations