© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12935
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to fantasy or science fiction settings

    oai_token-act-pair · gemini-2.0-flash

    setting/time period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    älde
    -0.50
     ElementRef
    -0.47
     SCOPE
    -0.43
    TRUNC
    -0.43
    emplar
    -0.43
     constitucional
    -0.43
    routeProvider
    -0.43
     Smithfield
    -0.43
     Jakub
    -0.42
     Capacidad
    -0.42
    POSITIVE LOGITS
    出版年
    0.73
    RTLD
    0.70
    findpost
    0.69
    tvguidetime
    0.67
    بوابة
    0.66
    /***/
    0.65
     виправивши
    0.63
     '\\;'
    0.63
    ArgumentParser
    0.62
    windowFixed
    0.61
    Activations Density 0.685%

    No Known Activations