© 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
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 10982
    Prev
    Next
    INDEX
    Explanations

    text that refers to financial reports or data

    oai_token-act-pair · gemini-2.0-flash

    Attributed quotes

    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
     ModelExpression
    -0.87
    StructEnd
    -0.64
     /\.(
    -0.64
     ProtoMessage
    -0.59
    __':
    
    -0.59
    DeleteBehavior
    -0.59
    WillAppear
    -0.57
    StoryboardSegue
    -0.56
    waitKey
    -0.56
    JAKARTA
    -0.56
    POSITIVE LOGITS
    TagMode
    0.60
    脚注の使い方
    0.57
    Clik
    0.57
     Rata
    0.54
    __(/*!
    0.52
    allclose
    0.50
    RATE
    0.49
     Kure
    0.49
    atrième
    0.48
     financières
    0.47
    Activations Density 0.482%

    No Known Activations