© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11004
    Prev
    Next
    INDEX
    Explanations

    code snippets that contain login related terms like "user", "password", and "email"

    oai_token-act-pair · gemini-2.0-flash

    say "Password"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    -0.69
     pengguna
    -0.63
     users
    -0.59
     USER
    -0.58
    user
    -0.58
     Users
    -0.57
    USER
    -0.54
    utilisateur
    -0.54
     User
    -0.53
     пользователя
    -0.52
    POSITIVE LOGITS
    Personendaten
    0.74
    SourceChecksum
    0.69
     otomatig
    0.67
    MigrationBuilder
    0.64
    ьаж
    0.63
     cherchés
    0.60
    istoitu
    0.60
     PyTuple
    0.59
    AsUp
    0.58
    DeleteBehavior
    0.57
    Activations Density 1.470%

    No Known Activations