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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 3950
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to social interactions, planning, or gatherings of people

    oai_token-act-pair · gemini-2.0-flash

    Specific gatherings or locations

    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
     University
    -1.12
     Bank
    -1.02
     College
    -1.02
     Court
    -1.02
     Hospital
    -0.99
     Resort
    -0.96
     Church
    -0.96
     School
    -0.96
    University
    -0.95
     Stadium
    -0.94
    POSITIVE LOGITS
     Author
    0.55
    Lyrics
    0.54
    Selected
    0.51
     Written
    0.50
    Contributor
    0.49
     Subject
    0.49
    جوايز
    0.49
    Author
    0.47
     Sting
    0.47
    Candidate
    0.46
    Activations Density 21.864%

    No Known Activations