© 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. 7230
    Prev
    Next
    INDEX
    Explanations

    first-person pronouns in narratives about personal relationships, preferences, or events, particularly in contexts involving judgments, decisions, or connections with others

    oai_token-act-pair · gemini-2.0-flash

    pronouns referring to people

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

    pronouns

    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
     my
    -1.14
     your
    -1.14
     you
    -1.11
    your
    -0.98
     we
    -0.87
    my
    -0.85
     meines
    -0.84
     Your
    -0.83
     me
    -0.80
    Your
    -0.77
    POSITIVE LOGITS
     they
    1.38
    They
    1.16
    they
    1.13
     They
    1.12
     he
    1.12
     mereka
    1.02
     them
    0.92
     они
    0.92
     он
    0.90
    他们
    0.90
    Activations Density 12.576%

    No Known Activations