© 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. 14267
    Prev
    Next
    INDEX
    Explanations

    uncertain questions or statements about possibilities and risks.

    oai_token-act-pair · gemini-2.0-flash

    variations of the verb "become"

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

    become

    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
     beijo
    -0.54
     Complementary
    -0.49
    FXML
    -0.48
    entennial
    -0.48
     geométrico
    -0.48
     TType
    -0.48
    idiary
    -0.48
     Vlas
    -0.48
    RefreshLayout
    -0.47
    WaitGroup
    -0.47
    POSITIVE LOGITS
     become
    2.73
     becoming
    2.63
     becomes
    2.47
    become
    2.44
     became
    2.42
     Become
    2.39
    becoming
    2.33
     Becoming
    2.31
    Becoming
    2.27
    Become
    2.19
    Activations Density 1.957%

    No Known Activations