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. 893
    Prev
    Next
    INDEX
    Explanations

    code that has a newline followed by a single digit activation value

    oai_token-act-pair · gemini-2.0-flash

    code

    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
    setVerticalGroup
    -0.91
    IRQn
    -0.79
    __(/*!
    -0.74
     للاسماء
    -0.72
    IUrlHelper
    -0.71
    rawDesc
    -0.71
     squared
    -0.69
     itſelf
    -0.68
     ISNI
    -0.67
    SourceChecksum
    -0.67
    POSITIVE LOGITS
    postValue
    0.60
    __':
    0.48
    <bos>
    0.42
     Just
    0.42
     just
    0.42
     تم
    0.42
     Ziel
    0.42
     bedienen
    0.42
    __':
    
    0.41
     Still
    0.41
    Activations Density 0.253%

    No Known Activations