© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 9465
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to marketing products and services.

    oai_token-act-pair · gemini-2.0-flash

    offers/deliveries

    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
     good
    -0.81
    good
    -0.81
    Good
    -0.74
    GOOD
    -0.66
     חיצוניים
    -0.66
     Good
    -0.64
    InstanceState
    -0.61
     GOOD
    -0.59
     buena
    -0.58
    Gute
    -0.54
    POSITIVE LOGITS
     over
    0.96
    over
    0.72
     OVER
    0.67
     Over
    0.62
    Over
    0.59
     ainfi
    0.59
     automatiques
    0.57
    تقاوى
    0.57
    archiviato
    0.57
    databind
    0.56
    Activations Density 11.581%

    No Known Activations