© 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. 11416
    Prev
    Next
    INDEX
    Explanations

    that it looks for prepositions and for elements of news about current events, like politics and elections

    oai_token-act-pair · gemini-2.0-flash

    social

    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
    艋
    -0.53
     ར
    -0.51
    posted
    -0.51
    Media
    -0.51
    媒体
    -0.51
    media
    -0.50
     Medien
    -0.50
     medier
    -0.50
     {:.
    -0.49
     media
    -0.49
    POSITIVE LOGITS
     social
    3.00
    social
    2.64
    Social
    2.56
     Social
    2.53
     SOCIAL
    2.36
    SOCIAL
    2.20
     sociale
    2.13
     sociales
    1.99
     sosial
    1.87
     sozialen
    1.87
    Activations Density 5.864%

    No Known Activations