© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 9656
    Prev
    Next
    INDEX
    Explanations

    words or phrases that express uncertainty or tentativeness

    oai_token-act-pair · gemini-2.0-flash

    modal verbs

    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
     Italijani
    -1.15
    HideFlags
    -0.94
     ویکی‌پدی
    -0.94
    Personendaten
    -0.85
     للاسماء
    -0.84
     varandra
    -0.83
    IsMutable
    -0.83
     fermés
    -0.82
     élevées
    -0.81
     vectorielles
    -0.81
    POSITIVE LOGITS
     a
    0.59
     just
    0.58
     me
    0.54
    ,
    0.53
     I
    0.52
     then
    0.52
     there
    0.50
     various
    0.49
     with
    0.48
     was
    0.47
    Activations Density 3.924%

    No Known Activations