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. 947
    Prev
    Next
    INDEX
    Explanations

    various forms of the constructor method "__init__" in Python

    oai_token-act-pair · gemini-2.0-flash

    init

    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
     Theſe
    -0.68
     becauſe
    -0.68
     purpoſe
    -0.65
     Majefty
    -0.65
     Monfieur
    -0.63
     myſelf
    -0.61
     ſtate
    -0.60
     whoſe
    -0.60
     themſelves
    -0.60
     pleaſure
    -0.57
    POSITIVE LOGITS
     resourceCulture
    0.54
    <bos>
    0.52
    erei
    0.44
    extendable
    0.42
    BIB
    0.42
     fur
    0.39
    Newswire
    0.39
    fut
    0.39
    openSession
    0.38
    cube
    0.38
    Activations Density 0.547%

    No Known Activations