© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 2898
    Prev
    Next
    INDEX
    Explanations

    instances of modal verbs like "can," "will," or "should" with an active sense.

    oai_token-act-pair · gemini-2.0-flash

    can

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     AppBundle
    -0.62
     ويمكن
    -0.59
    はじめに
    -0.58
     can
    -0.57
     Roskov
    -0.55
    TypedDataSet
    -0.52
     entweder
    -0.52
    can
    -0.51
    horabuena
    -0.51
     einde
    -0.50
    POSITIVE LOGITS
    ">//
    0.58
    SharedModule
    0.54
    RTLR
    0.52
    IndentedString
    0.52
    borderSide
    0.51
    ⓘ
    0.49
     poved
    0.49
    htë
    0.48
    InstrumentedTest
    0.48
    aurora
    0.47
    Activations Density 33.764%

    No Known Activations