© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4542
    Prev
    Next
    INDEX
    Explanations

    dollar amounts

    oai_token-act-pair · gemini-2.0-flash

    Currency amounts

    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
     million
    -0.96
     miljoen
    -0.90
     millioner
    -0.89
     Millionen
    -0.85
     milhões
    -0.83
     миллионов
    -0.82
     millions
    -0.81
    NewUrlParser
    -0.80
     میلیون
    -0.80
    million
    -0.80
    POSITIVE LOGITS
     Audiodateien
    0.69
    QRect
    0.52
    args
    0.52
    Портали
    0.50
    EAR
    0.50
    jard
    0.49
     EAR
    0.49
     HUND
    0.49
     args
    0.48
     hundred
    0.48
    Activations Density 1.187%

    No Known Activations