© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14106
    Prev
    Next
    INDEX
    Explanations

    instances of emotional language or personal interaction.

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "you"

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

    your you

    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
     hers
    -0.63
    her
    -0.56
     jestem
    -0.53
    ようだ
    -0.52
     ihn
    -0.50
    mine
    -0.49
     her
    -0.49
     mine
    -0.47
    him
    -0.47
    だが
    -0.47
    POSITIVE LOGITS
     your
    2.61
     you
    2.31
    your
    2.14
     yourself
    2.08
    Your
    1.95
     yourselves
    1.94
     Your
    1.86
     YOUR
    1.71
    you
    1.64
    YOUR
    1.64
    Activations Density 4.423%

    No Known Activations