© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13020
    Prev
    Next
    INDEX
    Explanations

    uses of the word "I" and "you", especially in questions

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "know."

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

    know

    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
    ̀nh
    -0.52
     Hara
    -0.47
    脚注の使い方
    -0.45
     Mess
    -0.45
    LookAnd
    -0.45
     出版
    -0.44
    fillType
    -0.43
    chez
    -0.43
    出版年
    -0.43
     super
    -0.42
    POSITIVE LOGITS
     know
    1.95
    know
    1.78
     knows
    1.77
     knew
    1.63
     knowing
    1.62
    Know
    1.62
     knowledge
    1.61
     Know
    1.55
     KNOW
    1.52
     Knowing
    1.51
    Activations Density 1.271%

    No Known Activations