© 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
    2. Gemma-2-2B
    3. 19-GEMMASCOPE-TRANSCODER-16K
    4. 1164
    Prev
    Next
    INDEX
    Explanations

    acts of thanking or acknowledging others

    oai_token-act-pair · gemini-2.0-flash

    thank

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    thâu
    -0.88
     Neander
    -0.75
    IntoConstraints
    -0.73
    writeFieldEnd
    -0.69
     TextAppearance
    -0.69
    DockStyle
    -0.69
     '\\;'
    -0.68
     Huguen
    -0.68
    StoryboardSegue
    -0.66
     Egli
    -0.66
    POSITIVE LOGITS
     all
    0.74
     everyone
    0.53
    Autoritní
    0.52
     the
    0.50
     each
    0.48
     for
    0.48
     K
    0.47
     O
    0.46
    all
    0.45
     All
    0.45
    Activations Density 5.540%

    No Known Activations