© 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. 3-GEMMASCOPE-TRANSCODER-16K
    4. 9830
    Prev
    Next
    INDEX
    Explanations

    words related to believing or thinking

    oai_token-act-pair · gemini-2.0-flash

    Forum posts/Conversations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     Audiodateien
    -0.64
    存于互联网档案馆
    -0.59
    ContentAsync
    -0.50
    versy
    -0.47
     specchio
    -0.46
     endereço
    -0.45
     parcheggio
    -0.45
     phénomène
    -0.44
     PLW
    -0.44
    éder
    -0.43
    POSITIVE LOGITS
     think
    2.31
     thought
    2.25
     THINK
    2.08
    thought
    2.06
    think
    2.06
     Thought
    2.03
     Think
    2.02
    Think
    2.00
    Thought
    1.99
     thinking
    1.95
    Activations Density 0.530%

    No Known Activations