© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 664
    Prev
    Next
    INDEX
    Explanations

    geographic place names, especially those in the Middle East

    oai_token-act-pair · gemini-2.0-flash

    east

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     estadual
    -0.51
     senderos
    -0.50
    Filmografie
    -0.48
    NewGuid
    -0.47
     mariana
    -0.47
     Juneau
    -0.47
     truff
    -0.46
    europa
    -0.46
     esempi
    -0.45
     planète
    -0.45
    POSITIVE LOGITS
    mybatisplus
    0.98
    AndEndTag
    0.93
    Personendaten
    0.79
    complexType
    0.75
     فريبيس
    0.74
    <bos>
    0.73
    клопе
    0.71
    twimg
    0.71
     Taktlose
    0.70
     beginnetje
    0.69
    Activations Density 0.745%

    No Known Activations