© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3956
    Prev
    Next
    INDEX
    Explanations

    place names, particularly cities and towns, possibly with associated state abbreviations or related terms

    oai_token-act-pair · gemini-2.0-flash

    locations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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>
    -0.49
    elemField
    -0.49
     متعلقه
    -0.49
    ніципалі
    -0.47
     שוליים
    -0.46
     nakalista
    -0.44
    ześnie
    -0.44
    idemiology
    -0.43
     الحره
    -0.42
     Hummel
    -0.41
    POSITIVE LOGITS
    mbggenerated
    0.63
    TagMode
    0.63
    脚注の使い方
    0.63
    LoggerFactory
    0.62
    Bibliograf
    0.61
    Bronnen
    0.58
    WebVitals
    0.58
    __':
    0.57
    irsi
    0.57
    Autoritní
    0.56
    Activations Density 0.713%

    No Known Activations