© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10476
    Prev
    Next
    INDEX
    Explanations

    discourse markers that hedge certainty and introduce alternatives.

    oai_token-act-pair · gemini-2.0-flash

    possibility

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     may
    -1.77
     might
    -1.71
     mungkin
    -1.56
    可能
    -1.53
     possibly
    -1.52
     likely
    -1.51
    might
    -1.50
    possibly
    -1.41
     Possibly
    -1.41
    may
    -1.40
    POSITIVE LOGITS
    contentLoaded
    0.67
     متعلقه
    0.59
     AssemblyTitle
    0.59
    __":
    0.58
    IActionResult
    0.54
    Cartney
    0.54
    emar
    0.52
    Бахар
    0.52
     Italijanski
    0.50
    zeba
    0.49
    Activations Density 1.809%

    No Known Activations