© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 7247
    Prev
    Next
    INDEX
    Explanations

    instances of the word "thus" or similar words related to logical consequence

    oai_token-act-pair · gemini-2.0-flash

    Thus

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    F
    -0.50
    As
    -0.50
    K
    -0.46
    R
    -0.45
    C
    -0.45
    U
    -0.44
    S
    -0.44
    I
    -0.42
    </strong>
    -0.42
    N
    -0.41
    POSITIVE LOGITS
    StoryboardSegue
    1.37
    ReusableCell
    1.06
    BufferException
    0.98
    ^(@)
    0.95
    rawDesc
    0.94
    protoimpl
    0.94
     ComVisible
    0.93
    IntoConstraints
    0.92
    ̈́
    0.91
    AllAfrica
    0.90
    Activations Density 3.705%

    No Known Activations