© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 7081
    Prev
    Next
    INDEX
    Explanations

    the word "care" and words that appear near this word.

    oai_token-act-pair · gemini-2.0-flash

    medical 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_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     care
    -2.94
     Care
    -2.94
    Care
    -2.88
    care
    -2.84
     CARE
    -2.58
    CARE
    -2.53
     cared
    -2.38
     caring
    -2.30
     cares
    -2.23
    Caring
    -2.11
    POSITIVE LOGITS
     án
    0.46
     ModelExpression
    0.45
     spal
    0.44
    ilst
    0.41
    torta
    0.40
     vestibule
    0.40
    CrossRef
    0.40
    Demografia
    0.39
    SocketAddress
    0.39
    AnimationsModule
    0.39
    Activations Density 1.413%

    No Known Activations