Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 8-GEMMASCOPE-TRANSCODER-16K
    4. 1170
    Prev
    Next
    INDEX
    Explanations

    words related to finance, taxation, and company reporting

    oai_token-act-pair · gemini-2.0-flash

    Finance/Accounting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     المعيارى
    -0.80
     متعلقه
    -0.75
    writeField
    -0.74
    GEBURTSDATUM
    -0.70
    BeginContext
    -0.69
     Majefty
    -0.66
    IndentedString
    -0.65
     isInitialized
    -0.65
     avoient
    -0.65
     distanciation
    -0.64
    POSITIVE LOGITS
     שוליים
    0.50
     καν
    0.49
    Atsauces
    0.47
    Literatur
    0.47
    ={},
    0.46
    zcz
    0.45
     \&
    0.45
    DialogTitle
    0.45
     Reg
    0.44
     reg
    0.43
    Activations Density 0.398%

    No Known Activations