© 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. 12489
    Prev
    Next
    INDEX
    Explanations

    code snippets which use SQL and refer to users

    oai_token-act-pair · gemini-2.0-flash

    user

    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
     User
    -0.75
     user
    -0.72
    user
    -0.70
    User
    -0.69
     personalise
    -0.62
    例文帳に追加
    -0.60
     personalisation
    -0.59
     Users
    -0.59
     USER
    -0.57
     cá
    -0.57
    POSITIVE LOGITS
     estekak
    0.69
     OSI
    0.68
     ContentValues
    0.67
    awtextra
    0.59
     Prü
    0.56
    JComboBox
    0.54
    litude
    0.53
     useRouter
    0.53
     }}"></
    0.52
    enschaft
    0.52
    Activations Density 4.181%

    No Known Activations