© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14017
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "the" or "deep" followed by a sentence fragment including a form of "can" or "do" followed by "care"

    oai_token-act-pair · gemini-2.0-flash

    variations of "care"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     habet
    -0.58
    JsonInclude
    -0.54
     Copernicus
    -0.53
    featureID
    -0.51
     geslacht
    -0.50
     AQUÍ
    -0.50
    DockStyle
    -0.50
     Để
    -0.49
    VersionUID
    -0.48
    Translator
    -0.47
    POSITIVE LOGITS
     care
    2.70
     Care
    2.23
     cared
    2.14
     cares
    2.11
    care
    2.09
     CARE
    2.05
     caring
    1.99
    Care
    1.92
    CARE
    1.77
     Caring
    1.64
    Activations Density 2.725%

    No Known Activations