© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 1442
    Prev
    Next
    INDEX
    Explanations

    the start of a newsletter and subscription information

    oai_token-act-pair · gemini-2.0-flash

    Newsletter

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    WithIOException
    -0.92
     Roskov
    -0.72
     للاسماء
    -0.68
    Попис
    -0.68
    AutoScaleMode
    -0.66
     صوتيه
    -0.66
     AspNetCore
    -0.62
     tartalomajánló
    -0.61
    InjectAttribute
    -0.59
     Monark
    -0.58
    POSITIVE LOGITS
    抜き
    0.47
    sheet
    0.47
    sheets
    0.47
     Issue
    0.45
     issue
    0.45
    Тру
    0.45
    endance
    0.45
     evit
    0.44
    єра
    0.44
     observación
    0.42
    Activations Density 0.327%

    No Known Activations