© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10065
    Prev
    Next
    INDEX
    Explanations

    words related to historical political agreements and rulers

    oai_token-act-pair · gemini-2.0-flash

    audience

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    rungsseite
    -0.84
     ligiloj
    -0.78
     متعلقه
    -0.76
    évaluateur
    -0.73
     pinulongan
    -0.73
    tagHelperRunner
    -0.69
    TagMode
    -0.68
    TargetException
    -0.67
     незавершена
    -0.65
    ništ
    -0.64
    POSITIVE LOGITS
     audience
    0.68
     audiences
    0.67
     Audience
    0.62
    audience
    0.62
    Audience
    0.60
    Audiences
    0.57
     bull
    0.52
     Audi
    0.47
    cheri
    0.47
     Bull
    0.46
    Activations Density 2.502%

    No Known Activations