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. 7-GEMMASCOPE-TRANSCODER-16K
    4. 6992
    Prev
    Next
    INDEX
    Explanations

    words and phrases that indicate two things have something in common with each other

    oai_token-act-pair · gemini-2.0-flash

    common

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     common
    -1.35
     Common
    -1.34
    Common
    -1.26
    common
    -1.26
     COMMON
    -1.15
    COMMON
    -1.09
     común
    -0.96
     communs
    -0.94
     comunes
    -0.93
     comune
    -0.87
    POSITIVE LOGITS
    <bos>
    0.54
    propTypes
    0.46
    Cubit
    0.45
     Préférences
    0.43
    awtextra
    0.42
    ;">
    
    0.42
    Uninitialized
    0.42
    httphttps
    0.42
    ंदीखरीदारी
    0.42
    tonode
    0.41
    Activations Density 19.789%

    No Known Activations