© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 10343
    Prev
    Next
    INDEX
    Explanations

    snippets of academic looking text, including citation markers, government related vocabulary, patent related vocabulary, illness, and vocabulary with certain prefixes

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    ंदीखरीदारी
    -0.45
    queryInterface
    -0.44
     архивлан
    -0.44
    <h6>
    -0.44
    — 
    -0.44
     ...
    -0.43
    ContentAsync
    -0.43
    ...
    -0.43
    ...");
    -0.42
    Portale
    -0.42
    POSITIVE LOGITS
    nds
    0.57
    Dl
    0.55
    Tm
    0.55
    Mst
    0.54
    Md
    0.54
     الاطلاع
    0.54
    Hl
    0.54
    nei
    0.53
    lw
    0.53
    Jn
    0.52
    Activations Density 11.985%

    No Known Activations