© 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. 9580
    Prev
    Next
    INDEX
    Explanations

    content related to financial accounts and legal or political accusations, often in a multilingual context (Portuguese, financial jargon, and code snippets mixed in).

    oai_token-act-pair · gemini-2.0-flash

    account

    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
     account
    -1.46
     accounts
    -1.34
     Account
    -1.28
     ACCOUNT
    -1.28
    account
    -1.23
    Account
    -1.21
     Accounts
    -1.21
     getAccount
    -1.11
    Accounts
    -1.05
    ACCOUNT
    -1.05
    POSITIVE LOGITS
    #+#
    0.52
     CommonModule
    0.52
    ConstraintMaker
    0.52
    Zacks
    0.51
    ActionCreators
    0.50
    iredo
    0.50
    APIView
    0.49
    GeneratedCode
    0.48
    knex
    0.48
    awtextra
    0.47
    Activations Density 22.746%

    No Known Activations