© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 3023
    Prev
    Next
    INDEX
    Explanations

    mentions of someone thinking, especially related to beliefs

    oai_token-act-pair · gemini-2.0-flash

    think

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     think
    -1.70
     thinks
    -1.48
    think
    -1.41
    Think
    -1.39
     Think
    -1.38
     THINK
    -1.38
     thinking
    -1.31
     thought
    -1.20
     believe
    -1.14
    THINK
    -1.10
    POSITIVE LOGITS
     darbo
    0.68
     väli
    0.65
    SharedCtor
    0.63
     OMITBAD
    0.61
     videre
    0.60
    AnchorStyles
    0.58
    Cyfarwyddwr
    0.57
    DockStyle
    0.57
     plát
    0.56
    AndroidJUnit
    0.56
    Activations Density 1.042%

    No Known Activations