© 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. 13571
    Prev
    Next
    INDEX
    Explanations

    personal pronouns and words connecting them to other words

    oai_token-act-pair · gemini-2.0-flash

    references to relationships or marital status

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

    close relationships

    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
    Посилання
    -0.54
    alité
    -0.50
     bed
    -0.47
     screwing
    -0.47
    లాలు
    -0.45
    其
    -0.45
     其
    -0.45
    centralwidget
    -0.45
     seus
    -0.44
    zeera
    -0.43
    POSITIVE LOGITS
    DockStyle
    0.66
     Husband
    0.64
    TagMode
    0.64
     husband
    0.63
    Personensuche
    0.63
    lwjgl
    0.62
    husband
    0.57
    GEBURTSDATUM
    0.57
     Anſ
    0.57
    feldt
    0.57
    Activations Density 1.564%

    No Known Activations