© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 12753
    Prev
    Next
    INDEX
    Explanations

    words within scientific or technical documents

    oai_token-act-pair · gemini-2.0-flash

    science

    np_max-act · gemini-2.0-flash

    weather

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     &___
    -0.83
    '])->
    -0.82
    CppMethod
    -0.80
    ]")]
    -0.74
    ContentAsync
    -0.71
    transQ
    -0.70
    EndInit
    -0.70
     ſeveral
    -0.69
     bezeichneter
    -0.69
    WebServlet
    -0.69
    POSITIVE LOGITS
    .
    0.68
    orological
    0.60
    orology
    0.58
     Meteoro
    0.53
     weather
    0.53
    Weather
    0.53
    '
    0.52
    potranspiration
    0.52
     meteoro
    0.49
    <bos>
    0.49
    Activations Density 4.186%

    No Known Activations