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. 749
    Prev
    Next
    INDEX
    Explanations

    conversation about documentary films

    oai_token-act-pair · gemini-2.0-flash

    Explanations

    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
    ContentAsync
    -0.66
     تضيفلها
    -0.62
     OMITBAD
    -0.60
     autorytatywna
    -0.53
     viewDidLoad
    -0.52
    DockStyle
    -0.51
    IndentedString
    -0.49
    WriteAttribute
    -0.49
    tein
    -0.47
     CURLOPT
    -0.47
    POSITIVE LOGITS
    ^(@)
    0.65
    paddingVertical
    0.65
     myſelf
    0.59
     himſelf
    0.59
    bruik
    0.56
     ujednoznacz
    0.55
     themſelves
    0.55
    ſelf
    0.55
     Efq
    0.55
     zufolge
    0.54
    Activations Density 0.913%

    No Known Activations