© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 10643
    Prev
    Next
    INDEX
    Explanations

    a mishmash of numbers, random characters, and common short words and verbs

    oai_token-act-pair · gemini-2.0-flash

    Scraped texts/code

    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
     himo
    -0.77
     hysteresis
    -0.76
     subgoals
    -0.74
     commutation
    -0.72
     extradition
    -0.72
     CommonModule
    -0.71
     translocation
    -0.69
     renunciation
    -0.69
    Cursors
    -0.68
     lagoons
    -0.67
    POSITIVE LOGITS
    出版年
    0.61
     Diakses
    0.52
     发表于
    0.44
     الحره
    0.44
    lloworld
    0.43
    Ђ
    0.43
    PMID
    0.42
      (
    0.41
    <thead>
    0.40
    ("")]
    0.40
    Activations Density 18.542%

    No Known Activations