© 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. 6905
    Prev
    Next
    INDEX
    Explanations

    computer code snippets and data structures, possibly related to data storage and error handling

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    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
     true
    -2.67
    true
    -2.47
    True
    -1.95
     TRUE
    -1.88
     True
    -1.85
    TRUE
    -1.68
    false
    -1.59
     vrai
    -1.56
     verdadero
    -1.48
     false
    -1.45
    POSITIVE LOGITS
    ides
    0.43
     Тип
    0.43
    bitur
    0.43
     هيا
    0.43
    reuth
    0.43
     Ball
    0.42
    Размер
    0.42
    uegos
    0.41
    neſs
    0.41
     Размер
    0.41
    Activations Density 0.718%

    No Known Activations