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. 0-GEMMASCOPE-TRANSCODER-16K
    4. 7122
    Prev
    Next
    INDEX
    Explanations

    code snippets, coding terms, or file names

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     cherchés
    -1.09
    BibitemShut
    -1.05
    etheless
    -0.96
    bibfield
    -0.96
     سكانية
    -0.93
    WriteTagHelper
    -0.91
    bibinfo
    -0.90
    })*/
    -0.88
    featureID
    -0.87
    NUMX
    -0.86
    POSITIVE LOGITS
    <bos>
    1.17
      
    0.73
        
    0.70
    _
    0.69
    &
    0.68
    @
    0.68
       
    0.67
    <strong>
    0.67
    <h1>
    0.66
    The
    0.66
    Activations Density 1.711%

    No Known Activations