© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11230
    Prev
    Next
    INDEX
    Explanations

    numerical data like dates, scores, results, and IDs

    oai_token-act-pair · gemini-2.0-flash

    eleven

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    تفصیلات
    -0.60
     متعلقه
    -0.50
    mergeFrom
    -0.48
    제
    -0.47
    Jeografia
    -0.47
     gyhoeddwyd
    -0.46
     thiệu
    -0.46
     vistos
    -0.46
    cass
    -0.45
     defaultstate
    -0.45
    POSITIVE LOGITS
     eleven
    0.80
    eleven
    0.76
     Eleven
    0.75
    ۱۱
    0.73
     XI
    0.72
     ELE
    0.68
    Filmographie
    0.67
    Eleven
    0.67
     eleventh
    0.65
     Eleventh
    0.64
    Activations Density 2.521%

    No Known Activations