© 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. 11071
    Prev
    Next
    INDEX
    Explanations

    phrases indicating uncertainty about the future and attempts to understand something

    oai_token-act-pair · gemini-2.0-flash

    expressing uncertainty

    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
     know
    -1.55
     knowing
    -1.52
     knows
    -1.42
    Know
    -1.41
     Knowing
    -1.40
    Knowing
    -1.39
     knew
    -1.37
    know
    -1.35
    knowing
    -1.31
     KNOW
    -1.30
    POSITIVE LOGITS
     يتيمه
    1.01
    AccessorTable
    0.80
    Personendaten
    0.79
    localctx
    0.67
    Vidite
    0.66
    ($__
    0.64
    AsUp
    0.64
    脚注の使い方
    0.63
    ArrowToggle
    0.62
    KEYCODE
    0.62
    Activations Density 1.625%

    No Known Activations