© 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. 7937
    Prev
    Next
    INDEX
    Explanations

    mentions of royalty and universities, with a strong affinity for "Queen"

    oai_token-act-pair · gemini-2.0-flash

    references to "Queen"

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

    Queen or Prince

    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
     Efq
    -0.53
     orale
    -0.46
     Eſ
    -0.45
    GRES
    -0.45
     ſhe
    -0.44
     kurulan
    -0.43
    SCIENCE
    -0.43
     Anſ
    -0.43
     ſeveral
    -0.43
     Reſ
    -0.42
    POSITIVE LOGITS
    tvguidetime
    0.74
    GEBURTSDATUM
    0.72
    NameInMap
    0.69
    AxisAlignment
    0.69
    ViewFeatures
    0.68
     CURIAM
    0.68
    Билгалдахарш
    0.66
     صوتيه
    0.65
    chengladbach
    0.65
    ContentAlignment
    0.63
    Activations Density 0.737%

    No Known Activations