© 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. 5224
    Prev
    Next
    INDEX
    Explanations

    words and phrases relate to sports statistics and contracts

    oai_token-act-pair · gemini-2.0-flash

    tokens or phrases with specific structural patterns

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

    say time period

    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
     ModelExpression
    -1.12
    
    -1.02
     EconPapers
    -1.02
    awtextra
    -0.89
     للاسماء
    -0.82
    fillType
    -0.80
    SourceChecksum
    -0.78
     تضيفلها
    -0.78
    UseVisualStyle
    -0.75
    脚注の使い方
    -0.74
    POSITIVE LOGITS
     of
    0.41
    '
    0.40
    ari
    0.39
     encor
    0.39
    擴
    0.39
     προσ
    0.39
     tiếp
    0.38
    H
    0.38
    asis
    0.36
     aimer
    0.36
    Activations Density 0.443%

    No Known Activations