© 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. 10441
    Prev
    Next
    INDEX
    Explanations

    Lithuanian words and place names

    oai_token-act-pair · gemini-2.0-flash

    io

    np_max-act · gemini-2.0-flash
    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
    <bos>
    -0.55
    uoja
    -0.52
     potreb
    -0.41
     támogat
    -0.41
    անո
    -0.41
     része
    -0.40
    cristo
    -0.40
    ítja
    -0.39
     مواليد
    -0.39
     olvas
    -0.38
    POSITIVE LOGITS
    تقاوى
    1.09
     فريبيس
    1.03
    tagHelperRunner
    0.98
     виправивши
    0.98
    IBAction
    0.96
    enumi
    0.96
     дописавши
    0.95
    TagMode
    0.94
    出版年
    0.92
    +#+#
    0.92
    Activations Density 0.137%

    No Known Activations