© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5281
    Prev
    Next
    INDEX
    Explanations

    financial terms and phrases related to loans, mortgages, and banking

    oai_token-act-pair · gemini-2.0-flash

    Mortgages and loans

    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
    hoon
    -0.56
    ellidos
    -0.48
    dw
    -0.47
    khana
    -0.45
     dân
    -0.44
    észet
    -0.44
     channel
    -0.43
    ネル
    -0.42
     الکترون
    -0.42
    cienti
    -0.40
    POSITIVE LOGITS
    BeginContext
    0.68
     FetchType
    0.65
     незавершена
    0.64
     nahilalakip
    0.63
     ExecuteAsync
    0.62
     يتيمه
    0.60
     endwhile
    0.60
    voerd
    0.59
     GenerationType
    0.58
    ReusableCell
    0.58
    Activations Density 1.539%

    No Known Activations