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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 6422
    Prev
    Next
    INDEX
    Explanations

    words, phrases, and viewpoints related to financial investments

    oai_token-act-pair · gemini-2.0-flash

    finance investment

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     investment
    -2.80
     Investment
    -2.59
    Investment
    -2.56
     invest
    -2.56
     investing
    -2.55
    investment
    -2.50
     investments
    -2.44
     INVEST
    -2.44
     Invest
    -2.42
     Investing
    -2.42
    POSITIVE LOGITS
    ⓧ
    0.66
     CreateTagHelper
    0.57
     bezeichneter
    0.50
    scrollLeft
    0.47
    multirow
    0.47
     Proctor
    0.46
    iencias
    0.46
    ůže
    0.45
    CCP
    0.44
    ГЛА
    0.43
    Activations Density 1.383%

    No Known Activations