© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 1862
    Prev
    Next
    INDEX
    Explanations

    mentions of specific organizations and financial matters like charges and traffic volume around those organizations

    oai_token-act-pair · gemini-2.0-flash

    business

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    Workbench
    -0.54
     pinulongan
    -0.53
    SuccessListener
    -0.49
    ))->
    -0.46
    мум
    -0.46
    AutoScaleMode
    -0.45
    ViewFeatures
    -0.45
     work
    -0.44
     CALENDAR
    -0.44
    Attributed
    -0.43
    POSITIVE LOGITS
     itſelf
    0.75
    rrggbb
    0.66
     myſelf
    0.64
     мәкал
    0.63
    RegressionTest
    0.60
     Monfieur
    0.60
     通販
    0.59
     Anſ
    0.59
     Réponses
    0.59
    فایل‌لار
    0.58
    Activations Density 1.777%

    No Known Activations