© 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
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6733
    Prev
    Next
    INDEX
    Explanations

    language used when people are trying to influence or deceive others

    oai_token-act-pair · gemini-2.0-flash

    thoughts and beliefs

    np_token-act-pair-logits · gpt-4o-mini

    think

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     оригіналу
    -0.76
    atste
    -0.56
     الدولى
    -0.53
    oa̍t
    -0.52
     uintptr
    -0.52
    AutoScaleMode
    -0.52
    RTEX
    -0.51
     Вікі
    -0.49
    DockStyle
    -0.48
    =(-
    -0.48
    POSITIVE LOGITS
     think
    2.23
     thinks
    2.02
     Think
    1.92
     thinking
    1.92
     THINK
    1.91
    think
    1.90
    Think
    1.88
    THINK
    1.73
     believe
    1.70
     thought
    1.69
    Activations Density 1.927%

    No Known Activations