© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9999
    Prev
    Next
    INDEX
    Explanations

    announcements, contracts, and agreements, especially those involving people, companies, and dates, and it especially emphasizes the act of signing.

    oai_token-act-pair · gemini-2.0-flash

    announce

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     announcing
    -1.01
     announcement
    -0.94
     announce
    -0.93
     announces
    -0.91
     announced
    -0.91
    announced
    -0.88
     ANNOUNC
    -0.86
     announcements
    -0.85
     Announces
    -0.84
     Announced
    -0.82
    POSITIVE LOGITS
    DotNetBar
    0.52
    рд
    0.49
    INPUTS
    0.47
    __":
    0.45
    __':
    0.44
    hawatir
    0.44
     deportivos
    0.43
     geleverd
    0.43
    deltaTime
    0.43
    󠁢
    0.42
    Activations Density 18.978%

    No Known Activations