© 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. 13123
    Prev
    Next
    INDEX
    Explanations

    proper nouns, locations, and words related to legal proceedings or geographical regions

    oai_token-act-pair · gemini-2.0-flash

    Australian news/companies

    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
     aged
    -0.69
     Aged
    -0.64
    Aged
    -0.62
     Labor
    -0.59
    ="<?
    -0.56
     WA
    -0.54
    Labor
    -0.52
    TabStop
    -0.52
     متعلقه
    -0.52
    setVerticalGroup
    -0.50
    POSITIVE LOGITS
    万美元
    0.67
     (£
    0.60
    -£
    0.56
    出版年
    0.56
    CloseOperation
    0.56
     Alamy
    0.55
    Yann
    0.54
    StringField
    0.54
    ৳
    0.53
     ANTONIO
    0.52
    Activations Density 3.187%

    No Known Activations