© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 2163
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to visiting historical locations and personal connections to the past

    oai_token-act-pair · gemini-2.0-flash

    places of death/birth

    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
    usky
    -0.45
    ื่อน
    -0.43
    iah
    -0.43
    chnet
    -0.42
     descuento
    -0.41
    лір
    -0.41
    ี้ยง
    -0.41
    ě
    -0.40
    ïse
    -0.40
    getParams
    -0.40
    POSITIVE LOGITS
     autorytatywna
    0.88
     Diſ
    0.71
     Majefty
    0.69
     greateſt
    0.67
     Inſ
    0.67
     ſeveral
    0.67
    FormTagHelper
    0.67
     ſame
    0.66
     Efq
    0.66
    KommentareTeilen
    0.65
    Activations Density 1.421%

    No Known Activations