© 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. 14233
    Prev
    Next
    INDEX
    Explanations

    numerical data, or possibly abstract concepts related to mathematics, or properties.

    oai_token-act-pair · gemini-2.0-flash

    numerical data

    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
    VersionUID
    -0.65
     vuitton
    -0.59
     estekak
    -0.58
    ikir
    -0.50
    Gob
    -0.50
    MINI
    -0.50
     miniatura
    -0.49
     widows
    -0.49
     probability
    -0.48
     demurrer
    -0.48
    POSITIVE LOGITS
     propOrder
    0.75
     ujednoznacz
    0.68
    exitRule
    0.62
    matchCondition
    0.56
     desertcart
    0.55
    فایل‌لار
    0.51
    allclose
    0.51
    তথ্যসূত্র
    0.51
    VELAND
    0.49
     CreateTagHelper
    0.49
    Activations Density 4.586%

    No Known Activations