© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9544
    Prev
    Next
    INDEX
    Explanations

    words or phrases that indicate change or departure from a team, job, or group.

    oai_token-act-pair · gemini-2.0-flash

    departure or termination

    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
    ynb
    -0.56
    hésite
    -0.52
     estekak
    -0.52
    lana
    -0.46
     ByteBuffer
    -0.46
     Freitas
    -0.46
     coaster
    -0.46
     Movements
    -0.45
     movements
    -0.45
    movements
    -0.45
    POSITIVE LOGITS
    jooq
    0.78
     initComponents
    0.60
    SharedDtor
    0.52
     Roskov
    0.51
    #
    0.50
    makeConstraints
    0.49
     يتيمه
    0.48
     nahilalakip
    0.48
    typeorm
    0.47
    Ign
    0.47
    Activations Density 1.203%

    No Known Activations