© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14095
    Prev
    Next
    INDEX
    Explanations

    the words "this," "that," "these," and other words that co-occur with those words

    oai_token-act-pair · gemini-2.0-flash

    this

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     surla
    -0.69
     Pura
    -0.59
     PopupWindow
    -0.57
     Normdatei
    -0.55
    Atentamente
    -0.54
     bona
    -0.54
    出版年
    -0.53
     itſelf
    -0.52
     gjen
    -0.52
    حياته
    -0.52
    POSITIVE LOGITS
    tagHelperRunner
    0.73
     autorytatywna
    0.66
    Autoritní
    0.65
    <bos>
    0.60
    IUrlHelper
    0.58
     %>%
    0.52
    localVar
    0.52
    Linki
    0.52
     चीज़ों
    0.50
     disambiguazione
    0.49
    Activations Density 2.168%

    No Known Activations