© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4952
    Prev
    Next
    INDEX
    Explanations

    code snippets dealing with error handling in go.

    oai_token-act-pair · gemini-2.0-flash

    error-related terms

    np_token-act-pair-logits · gpt-4o-mini

    err

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    yo
    -0.55
     adapters
    -0.54
     econ
    -0.54
    sal
    -0.53
    Abitanti
    -0.52
    Sal
    -0.50
     hab
    -0.50
     glassware
    -0.49
    ~
    -0.48
    Station
    -0.48
    POSITIVE LOGITS
    berdayakan
    0.69
     démocr
    0.67
     Wikiseite
    0.67
     незавершена
    0.65
     rapides
    0.62
    extAlignment
    0.60
    mặt
    0.60
     commerciales
    0.59
     Мексичка
    0.59
     betweenstory
    0.59
    Activations Density 0.710%

    No Known Activations