© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9201
    Prev
    Next
    INDEX
    Explanations

    references to publications or websites, including bracketed titles, conference names, and URLs

    oai_token-act-pair · gemini-2.0-flash

    date-related terms or months

    np_token-act-pair-logits · gpt-4o-mini

    punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    InjectAttribute
    -0.86
    TestingModule
    -0.77
    SequentialGroup
    -0.77
    TargetException
    -0.73
    TagHelper
    -0.73
    SpringBootTest
    -0.70
     Waray
    -0.69
    EnumMember
    -0.69
     تضيفلها
    -0.67
    IsContent
    -0.67
    POSITIVE LOGITS
     October
    0.43
     March
    0.41
    чої
    0.40
     (
    0.39
     Sept
    0.39
     транспорта
    0.38
    ių
    0.38
    плі
    0.38
     Oct
    0.38
     ver
    0.38
    Activations Density 2.342%

    No Known Activations