© 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. 5433
    Prev
    Next
    INDEX
    Explanations

    words related to groups of people, awards, movies, news, destinations, and other various topics

    oai_token-act-pair · gemini-2.0-flash

    Groups of people

    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
     who
    -1.24
    who
    -1.16
    Who
    -1.08
     Who
    -1.06
     WHO
    -0.91
     quien
    -0.85
    WHO
    -0.84
     whom
    -0.81
    quién
    -0.79
     quién
    -0.79
    POSITIVE LOGITS
     kaarangay
    0.83
    iastes
    0.70
    Personendaten
    0.68
    XmlEnum
    0.66
    BeginContext
    0.63
    adpleegd
    0.63
    ggars
    0.63
     Савезне
    0.62
    HasAnnotation
    0.62
    oredCriteria
    0.61
    Activations Density 20.866%

    No Known Activations