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. 20-GEMMASCOPE-TRANSCODER-16K
    4. 14638
    Prev
    Next
    INDEX
    Explanations

    mentions of 'Player of the Year'

    oai_token-act-pair · gemini-2.0-flash

    awards and recognitions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    of
    -0.60
    ,
    -0.60
     v
    -0.59
    Of
    -0.56
     of
    -0.56
     “
    -0.56
     un
    -0.56
     M
    -0.55
     "
    -0.55
     A
    -0.54
    POSITIVE LOGITS
     itſelf
    1.06
     Theſe
    1.06
     myſelf
    1.02
     дописавши
    1.00
    expandindo
    0.96
    RenderAtEndOf
    0.96
     Efq
    0.95
    AddTagHelper
    0.95
     Monfieur
    0.94
     Shakspeare
    0.93
    Activations Density 0.303%

    No Known Activations