© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 13402
    Prev
    Next
    INDEX
    Explanations

    terms related to legal and official documents, and sometimes medical or scientific documents.

    oai_token-act-pair · gemini-2.0-flash

    Authority figures or positions

    np_max-act · gemini-2.0-flash

    leadership roles

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
     curator
    -0.48
    @[+][
    -0.48
     kee
    -0.45
     Spirito
    -0.44
    ard
    -0.43
    asz
    -0.43
    fillType
    -0.43
     investigator
    -0.43
     manager
    -0.42
     Curator
    -0.42
    POSITIVE LOGITS
    BufferException
    0.76
    NOPQRST
    0.67
    UnknownFieldSet
    0.66
     CreateTagHelper
    0.64
    WithIOException
    0.62
    InjectAttribute
    0.60
    లాలు
    0.59
    basicConfig
    0.59
     IDisposable
    0.57
    intahan
    0.57
    Activations Density 32.138%

    No Known Activations