© 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. 1093
    Prev
    Next
    INDEX
    Explanations

    transitional words combined with the word 'be'

    oai_token-act-pair · 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
    cèse
    -0.82
    findpost
    -0.69
    MessageTagHelper
    -0.67
    WithIOException
    -0.63
     jScrollPane
    -0.62
    mybatisplus
    -0.62
     SearchView
    -0.62
    ंदीखरीदारी
    -0.61
    contentLoaded
    -0.60
     оригіналу
    -0.59
    POSITIVE LOGITS
     becoming
    0.56
     visit
    0.51
     jesteś
    0.51
     as
    0.48
     visits
    0.46
    zyny
    0.46
    visitor
    0.46
    KURZBESCHREIBUNG
    0.46
     an
    0.45
     Wirklichkeit
    0.44
    Activations Density 1.529%

    No Known Activations