© 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. 9893
    Prev
    Next
    INDEX
    Explanations

    countries

    oai_token-act-pair · gemini-2.0-flash

    countries

    np_max-act-logits · gemini-2.0-flash

    list separators

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
    ulously
    -0.48
    pull
    -0.48
    хь
    -0.48
    Pull
    -0.47
     mắn
    -0.47
     galvan
    -0.47
     PULL
    -0.47
    isContained
    -0.46
     pulling
    -0.45
     pulled
    -0.44
    POSITIVE LOGITS
    Romania
    0.88
    Bolivia
    0.85
    Latvia
    0.85
    Slovakia
    0.83
     Romanian
    0.82
    Lithuania
    0.82
    Estonia
    0.82
     Czech
    0.82
     Estonia
    0.81
     Latvian
    0.80
    Activations Density 17.064%

    No Known Activations