© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 13697
    Prev
    Next
    INDEX
    Explanations

    instances of uncertainty, tentativeness or doubt, particularly expressed with the word "is"

    oai_token-act-pair · gemini-2.0-flash

    is

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    principalTable
    -0.82
    rungsseite
    -0.68
    }{*}{
    -0.68
    šė
    -0.60
     []).
    -0.59
    WithIOException
    -0.58
     propOrder
    -0.58
     Италијани
    -0.57
     Periods
    -0.57
    itres
    -0.56
    POSITIVE LOGITS
    kheim
    0.43
    potranspiration
    0.41
    openhauer
    0.41
    Xna
    0.41
    
    0.40
    Sk
    0.39
    Tuber
    0.39
    ёз
    0.39
    FontAwesomeIcon
    0.39
     Suff
    0.38
    Activations Density 4.407%

    No Known Activations