© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15836
    Prev
    Next
    INDEX
    Explanations

    words related to functions or systems, including computing and the body

    oai_token-act-pair · gemini-2.0-flash

    technical processes

    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
     InputDecoration
    -0.75
    ագրություններ
    -0.57
     hàm
    -0.57
    ]=>
    -0.56
    SharedDtor
    -0.53
    WebServlet
    -0.52
    hyrchwyd
    -0.50
    Bibliographie
    -0.50
    xodo
    -0.50
    numbered
    -0.49
    POSITIVE LOGITS
     CreateTagHelper
    0.64
    лактика
    0.53
    errHandler
    0.52
    forName
    0.51
     呢
    0.46
     date
    0.46
    CopyWith
    0.45
    jsii
    0.45
    PageModule
    0.45
     frasco
    0.45
    Activations Density 21.848%

    No Known Activations