© 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. 9886
    Prev
    Next
    INDEX
    Explanations

    language in financial reports

    oai_token-act-pair · gemini-2.0-flash

    Company strategy

    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
     '\\;'
    -0.82
    MigrationBuilder
    -0.80
     AssemblyCompany
    -0.77
     fieldNum
    -0.72
    +#+
    -0.71
     يتيمه
    -0.71
    expandindo
    -0.67
     betweenstory
    -0.67
    Dữ
    -0.64
     Jefus
    -0.64
    POSITIVE LOGITS
     Hutton
    0.52
    iastes
    0.47
    burton
    0.46
     Rukh
    0.45
     execute
    0.44
     executing
    0.43
    ulta
    0.43
     Besch
    0.43
     execution
    0.42
    enty
    0.42
    Activations Density 1.108%

    No Known Activations