© 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. 4001
    Prev
    Next
    INDEX
    Explanations

    words related to institutions or organizations

    oai_token-act-pair · gemini-2.0-flash

    organizations and roles

    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
    lyde
    -0.51
     warping
    -0.50
    manager
    -0.50
     prophylaxis
    -0.50
    management
    -0.48
     solver
    -0.47
    LayoutConstraint
    -0.47
    ciaal
    -0.46
    MANAGEMENT
    -0.46
     redistribution
    -0.46
    POSITIVE LOGITS
    TagMode
    0.58
     चीज़ों
    0.57
    出版年
    0.54
     Holders
    0.53
     dabei
    0.49
     Caucus
    0.47
     Vitae
    0.46
     مواليد
    0.46
     Cabin
    0.46
     pretty
    0.46
    Activations Density 9.519%

    No Known Activations