© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15519
    Prev
    Next
    INDEX
    Explanations

    language related to health risks and preventative measures, especially with an authoritative tone

    oai_token-act-pair · gemini-2.0-flash

    Code and website features

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     tartalomajánló
    -1.02
     NSCoder
    -0.93
    adaptiveStyles
    -0.90
    BibitemShut
    -0.87
     <=",
    -0.85
     للمعارف
    -0.83
    verwijspagina
    -0.81
     itſelf
    -0.80
    évaluateur
    -0.80
     myſelf
    -0.78
    POSITIVE LOGITS
     
    0.46
     su
    0.46
     to
    0.45
    unsqueeze
    0.45
     Home
    0.44
    c
    0.43
    |
    0.42
     #
    0.42
    Hol
    0.41
     hela
    0.41
    Activations Density 0.130%

    No Known Activations