© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10292
    Prev
    Next
    INDEX
    Explanations

    words suggesting tentative thinking or opinion

    oai_token-act-pair · gemini-2.0-flash

    references to personal opinions or suggestions

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

    think

    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
    cogn
    -0.43
    нка
    -0.41
     think
    -0.39
    ]][
    -0.38
    sim
    -0.38
    ̣t
    -0.38
    ][
    -0.38
    yelidikan
    -0.37
    jamos
    -0.37
    bul
    -0.36
    POSITIVE LOGITS
     it
    0.90
     its
    0.87
    AccessorTable
    0.84
    webElementXpaths
    0.84
    InstrumentedTest
    0.84
     Савезне
    0.82
    IContainer
    0.81
     Paglinawan
    0.79
    setVerticalGroup
    0.79
    mybatisplus
    0.78
    Activations Density 3.180%

    No Known Activations