© 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. 13249
    Prev
    Next
    INDEX
    Explanations

    pronouns or articles preceding or following an adjective or a verb or emotion-laden language associated with people and their relationships.

    oai_token-act-pair · gemini-2.0-flash

    words related to concern and worry

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

    concern worry

    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
    tagHelperRunner
    -0.79
    expandindo
    -0.68
    queryInterface
    -0.62
     تضيفلها
    -0.59
     typelib
    -0.58
    StructEnd
    -0.58
    "])
    -0.57
     newBuilder
    -0.57
    invokeLater
    -0.57
    ///</
    -0.56
    POSITIVE LOGITS
     concern
    1.70
     Concern
    1.56
     concerned
    1.56
     worry
    1.50
     worried
    1.48
    Concern
    1.46
     Worry
    1.41
     CONCERN
    1.41
    concern
    1.38
     Concerned
    1.33
    Activations Density 1.381%

    No Known Activations