© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10504
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to financial investments and companies

    oai_token-act-pair · gemini-2.0-flash

    financial investments

    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
    WriteTagHelper
    -0.68
    fjspx
    -0.64
     виправивши
    -0.63
     investing
    -0.61
     inves
    -0.61
    GIVEREF
    -0.57
    utilisons
    -0.57
    AddTagHelper
    -0.56
     invests
    -0.56
     invested
    -0.54
    POSITIVE LOGITS
     Administrativna
    0.65
    titleMargin
    0.54
    脚注の使い方
    0.53
    ьаж
    0.49
     Prussia
    0.47
    etsu
    0.47
    CodeAttribute
    0.47
     ostavi
    0.46
    مث
    0.45
     IMPLIED
    0.45
    Activations Density 0.887%

    No Known Activations