© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5042
    Prev
    Next
    INDEX
    Explanations

    wording in business reports about current performance and future expectations.

    oai_token-act-pair · gemini-2.0-flash

    Financial reports

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     betweenstory
    -0.87
     OFDb
    -0.85
    setVerticalGroup
    -0.79
    BeginContext
    -0.72
    зулта
    -0.69
    InSection
    -0.68
    Autoritní
    -0.66
    IsContent
    -0.66
    出版年
    -0.66
     mergeFrom
    -0.66
    POSITIVE LOGITS
    engertian
    0.44
     Dign
    0.40
    ineas
    0.40
    ávají
    0.39
    zeichnung
    0.38
    лайн
    0.37
     kvě
    0.37
    átní
    0.37
    řízení
    0.37
    ago
    0.36
    Activations Density 2.076%

    No Known Activations