© 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. 14522
    Prev
    Next
    INDEX
    Explanations

    code syntax and code-related questions

    oai_token-act-pair · gemini-2.0-flash

    code/math

    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
    enumerate
    -1.19
    OGND
    -0.89
     ExecuteAsync
    -0.85
     Roskov
    -0.80
    ParallelGroup
    -0.75
    WithIOException
    -0.74
    +#+#
    -0.74
     تانيه
    -0.69
     snippetHide
    -0.69
    AddHtmlAttribute
    -0.68
    POSITIVE LOGITS
    ULING
    0.54
    istö
    0.48
    ggior
    0.47
    mbia
    0.47
     US
    0.47
    couvrez
    0.45
    RTRS
    0.44
    ELAND
    0.43
    OLE
    0.43
    easeOut
    0.43
    Activations Density 5.627%

    No Known Activations