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. 7146
    Prev
    Next
    INDEX
    Explanations

    the word "Great" and words with positive connotations

    oai_token-act-pair · gemini-2.0-flash

    Great

    np_max-act · 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
      
    -1.23
    ↵↵
    -1.09
     The
    -1.00
     But
    -0.97
     
    -0.97
     A
    -0.96
       
    -0.92
     Little
    -0.90
     No
    -0.89
    <eos>
    -0.89
    POSITIVE LOGITS
     auffi
    1.26
     purpoſe
    1.08
     ſmall
    1.04
     ſtate
    1.01
     ſche
    1.00
     RestTemplate
    0.97
     faſt
    0.97
     ſhe
    0.97
     noft
    0.96
     myſelf
    0.96
    Activations Density 1.432%

    No Known Activations