© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 4021
    Prev
    Next
    INDEX
    Explanations

    conjunctions and articles, especially 'and' and 'that'

    oai_token-act-pair · gemini-2.0-flash

    and/but

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     then
    -0.63
    Then
    -0.60
     Then
    -0.59
     Subsequently
    -0.58
    then
    -0.58
    そして
    -0.55
     and
    -0.52
     luego
    -0.52
     Luego
    -0.50
     Later
    -0.49
    POSITIVE LOGITS
     there
    0.82
    WriteTagHelper
    0.79
    UpInside
    0.73
     تضيفلها
    0.68
     viewType
    0.68
     as
    0.65
    twimg
    0.64
     claimants
    0.61
     poveznice
    0.61
    ConstraintMaker
    0.61
    Activations Density 4.939%

    No Known Activations