© 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. 15029
    Prev
    Next
    INDEX
    Explanations

    words that serve as prepositions and conjunctions as well as related adverbs

    oai_token-act-pair · gemini-2.0-flash

    prepositions in complex sentences

    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
    Personendaten
    -0.64
    wahati
    -0.56
     pregunto
    -0.55
    apunov
    -0.55
    tagHelperRunner
    -0.55
    racene
    -0.52
    SourceChecksum
    -0.51
    invokeLater
    -0.49
    protoc
    -0.49
    IsContent
    -0.49
    POSITIVE LOGITS
     butterknife
    0.59
     BorderRadius
    0.53
     DialogResult
    0.51
     ActionBar
    0.49
    indakan
    0.49
    setupUi
    0.47
    Between
    0.47
     TextAppearance
    0.46
    ::$_
    0.45
     gib
    0.45
    Activations Density 9.280%

    No Known Activations