© 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. 12624
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal/political agreements and scientific observations with a common word "concerned".

    oai_token-act-pair · gemini-2.0-flash

    Expressing 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_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
     concern
    -2.83
     Concern
    -2.69
    Concern
    -2.52
     concerns
    -2.50
    concern
    -2.47
     worry
    -2.45
     concerned
    -2.41
     Concerns
    -2.39
     CONCERN
    -2.39
     Worry
    -2.30
    POSITIVE LOGITS
     дописавши
    0.69
    IContainer
    0.54
    ніципалі
    0.49
    otides
    0.46
    पया
    0.46
    Sucesor
    0.46
     rhestr
    0.46
     кӀош
    0.45
    ]();
    0.45
     Económica
    0.45
    Activations Density 2.948%

    No Known Activations