© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 16210
    Prev
    Next
    INDEX
    Explanations

    code-related terms like "role" and names of UI elements

    oai_token-act-pair · gemini-2.0-flash

    code identifiers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    cityId
    -0.81
     K
    -0.81
     L
    -0.79
    UserDTO
    -0.78
     Y
    -0.78
    playerId
    -0.77
     E
    -0.77
    roleId
    -0.76
     G
    -0.76
     he
    -0.76
    POSITIVE LOGITS
     myſelf
    1.96
     purpoſe
    1.87
     ſtate
    1.78
     Monfieur
    1.73
     deſt
    1.71
     pleaſure
    1.71
     uſed
    1.70
     cauſe
    1.69
     Reſ
    1.68
     raiſ
    1.66
    Activations Density 0.663%

    No Known Activations