© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5571
    Prev
    Next
    INDEX
    Explanations

    financial information, including numbers, stocks, and dividends.

    oai_token-act-pair · gemini-2.0-flash

    terms related to shares and stock

    np_token-act-pair-logits · gpt-4o-mini

    share

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    évaluateur
    -0.65
    Šaltiniai
    -0.59
    AsUp
    -0.57
     Trustee
    -0.57
    存于互联网档案馆
    -0.57
    ativement
    -0.57
     autorytatywna
    -0.57
    posedge
    -0.54
    ArgumentParser
    -0.53
     CreateTagHelper
    -0.52
    POSITIVE LOGITS
     share
    1.59
     shares
    1.59
    share
    1.29
     Share
    1.28
    Share
    1.26
    shares
    1.24
     Shares
    1.23
    Shares
    1.15
     SHARE
    1.13
     sharing
    1.06
    Activations Density 2.444%

    No Known Activations