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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13832
    Prev
    Next
    INDEX
    Explanations

    words that express certainty or uncertainty

    oai_token-act-pair · gemini-2.0-flash

    certainly/definitely

    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
    InvalidProtocol
    -0.77
    SPJ
    -0.75
     getItemCount
    -0.74
    IVEREF
    -0.73
     विश्वसनीयता
    -0.73
    MemoryWarning
    -0.72
    Einfach
    -0.71
    eraard
    -0.71
    اریخ
    -0.71
    FunctionFlags
    -0.70
    POSITIVE LOGITS
     côtés
    0.47
    guém
    0.42
    atius
    0.42
     see
    0.41
     rangs
    0.41
     vatt
    0.40
     intérêt
    0.38
     rätt
    0.37
    חת
    0.37
    動
    0.36
    Activations Density 2.229%

    No Known Activations