© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14504
    Prev
    Next
    INDEX
    Explanations

    text about lawyers providing testimony about corruption scandals in Brazil and Wall Street

    oai_token-act-pair · gemini-2.0-flash

    corruption

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    <bos>
    -0.83
     giugno
    -0.42
     usually
    -0.42
     always
    -0.40
    いつも
    -0.40
     usual
    -0.40
     =
    -0.39
     stå
    -0.38
    MR
    -0.38
    mr
    -0.37
    POSITIVE LOGITS
    UnknownFieldSet
    0.81
     Majefty
    0.81
    Hochspringen
    0.81
     Jefus
    0.76
    AddTagHelper
    0.76
    UnitTesting
    0.74
     Diſ
    0.74
     &___
    0.73
    MessageTagHelper
    0.72
    ſelves
    0.72
    Activations Density 2.294%

    No Known Activations