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. 23-GEMMASCOPE-TRANSCODER-16K
    4. 12189
    Prev
    Next
    INDEX
    Explanations

    code snippets related to Microsoft Excel

    oai_token-act-pair · gemini-2.0-flash

    Microsoft Office/Excel context

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     autorytatywna
    -0.83
    neſs
    -0.73
    ſelf
    -0.70
     itſelf
    -0.67
    BufferException
    -0.66
     समीक्षाएं
    -0.65
     Pingback
    -0.65
    MIDDLEWARE
    -0.65
     समीक्षक
    -0.65
    intenance
    -0.64
    POSITIVE LOGITS
    PICT
    0.52
     kasarigan
    0.48
     Band
    0.47
    Band
    0.45
     Pra
    0.43
     Open
    0.42
     Insurance
    0.41
    ographiques
    0.41
    BAND
    0.40
    W
    0.40
    Activations Density 3.501%

    No Known Activations