© 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. 12366
    Prev
    Next
    INDEX
    Explanations

    content from legal documents combined with code

    oai_token-act-pair · gemini-2.0-flash

    variations of the number eight

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

    Number 8

    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
     cherchés
    -0.47
    TEMPLATE
    -0.45
    glises
    -0.45
     semicirc
    -0.42
    
    -0.41
    glTex
    -0.40
    izon
    -0.40
     soluble
    -0.40
    runde
    -0.40
    soluble
    -0.40
    POSITIVE LOGITS
    8
    0.93
     eighth
    0.89
     Eight
    0.85
     eight
    0.83
     Eighth
    0.83
     huit
    0.80
    eight
    0.78
    ８
    0.75
     oito
    0.75
    Eight
    0.75
    Activations Density 2.580%

    No Known Activations