© 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. 242
    Prev
    Next
    INDEX
    Explanations

    mentions of political and historical events, people, and organizations.

    oai_token-act-pair · gemini-2.0-flash

    period

    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
     Latimer
    -0.61
     Magee
    -0.57
     Hammond
    -0.57
     Dickerson
    -0.56
     Langford
    -0.55
     Dobson
    -0.54
     Stubbs
    -0.53
    SharedDtor
    -0.52
     Buckley
    -0.52
     McAllister
    -0.52
    POSITIVE LOGITS
     Igbo
    0.61
     Mughal
    0.59
     Merdeka
    0.58
     Rohing
    0.58
    Allah
    0.58
     Ratu
    0.57
     Zapo
    0.57
     Zoro
    0.57
     Uy
    0.57
     Puja
    0.57
    Activations Density 20.093%

    No Known Activations