© 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. 3592
    Prev
    Next
    INDEX
    Explanations

    words frequently occurring in the text, especially function words and some adjectives

    oai_token-act-pair · gemini-2.0-flash

    terms related to marriage

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

    Marriage

    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
    ISupport
    -0.67
    іга
    -0.46
    Geografía
    -0.46
    Халык
    -0.44
    urement
    -0.43
    setStyleSheet
    -0.42
     velkommen
    -0.42
    UserType
    -0.42
    terscotch
    -0.41
    linger
    -0.41
    POSITIVE LOGITS
     wife
    1.51
     husband
    1.23
     wives
    1.20
     Wife
    1.20
    wife
    1.18
     WIFE
    1.17
     Husband
    1.05
    Wife
    1.04
     spouses
    1.02
    husband
    1.01
    Activations Density 2.355%

    No Known Activations